< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6305 in Layer 27

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.5058. Min Range: -10.5058

Max Act: 10.5058. Min Act: -0.1700

Data Index: 3831193 (Open Web Text)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.7558. Min Act: -0.1700

Data Index: 1084389 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.6933. Min Act: -0.1700

Data Index: 5375855 (Open Web Text)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.6308. Min Act: -0.1700

Data Index: 2556709 (Open Web Text)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.6308. Min Act: -0.1700

Data Index: 8142112 (Open Web Text)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.5683. Min Act: -0.1700

Data Index: 8167383 (Open Web Text)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.5683. Min Act: -0.1700

Data Index: 6885241 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.4433. Min Act: -0.1700

Data Index: 1297029 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.4433. Min Act: -0.1700

Data Index: 1870951 (Open Web Text)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3808. Min Act: -0.1700

Data Index: 5044388 (Open Web Text)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3808. Min Act: -0.1700

Data Index: 3770355 (Open Web Text)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3808. Min Act: -0.1700

Data Index: 6978429 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.4433. Min Act: -0.1700

Data Index: 2121897 (Open Web Text)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3183. Min Act: -0.1700

Data Index: 4708446 (Open Web Text)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3183. Min Act: -0.1700

Data Index: 5035876 (Open Web Text)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3183. Min Act: -0.1700

Data Index: 5852295 (Open Web Text)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3183. Min Act: -0.1700

Data Index: 2023682 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.3183. Min Act: -0.1700

Data Index: 6944432 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.2558. Min Act: -0.1700

Data Index: 730509 (Open Web Text)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.5058. Min Range: -10.5058

Max Act: 9.2558. Min Act: -0.1700

Data Index: 4009242 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #19