< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 48 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.6958. Min Act: -0.1700

Data Index: 5288826 (Open Web Text)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.6958. Min Act: -0.1700

Data Index: 468883 (Open Web Text)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.1958. Min Act: -0.1700

Data Index: 4641148 (Open Web Text)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.2583. Min Act: -0.1700

Data Index: 414007 (Open Web Text)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.1333. Min Act: -0.1700

Data Index: 5773114 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0708. Min Act: -0.1700

Data Index: 1460570 (Open Web Text)

Max Activating Token Index: 945

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.1333. Min Act: -0.1700

Data Index: 3768845 (Open Web Text)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.1333. Min Act: -0.1700

Data Index: 8059079 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.1333. Min Act: -0.1700

Data Index: 2831920 (Open Web Text)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.1333. Min Act: -0.1700

Data Index: 444018 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0708. Min Act: -0.1700

Data Index: 5046230 (Open Web Text)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0708. Min Act: -0.1700

Data Index: 1822171 (Open Web Text)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0708. Min Act: -0.1700

Data Index: 1284071 (Open Web Text)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0083. Min Act: -0.1700

Data Index: 5410323 (Open Web Text)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0083. Min Act: -0.1700

Data Index: 4365725 (Open Web Text)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0083. Min Act: -0.1700

Data Index: 1756469 (Open Web Text)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.6958. Min Range: -10.6958

Max Act: 10.0083. Min Act: -0.1700

Data Index: 4176026 (Open Web Text)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.6958. Min Range: -10.6958

Max Act: 9.9458. Min Act: -0.1700

Data Index: 6766181 (Open Web Text)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.6958. Min Range: -10.6958

Max Act: 9.8833. Min Act: -0.1700

Data Index: 6913807 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.6958. Min Range: -10.6958

Max Act: 9.9458. Min Act: -0.1700

Data Index: 1017440 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #19