< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 9 in Layer 29

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.7083. Min Act: -0.1700

Data Index: 1788735 (Open Web Text)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3333. Min Act: -0.1700

Data Index: 5018719 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.3020. Min Act: -0.1700

Data Index: 2978699 (Open Web Text)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.2708. Min Act: -0.1700

Data Index: 2294824 (Open Web Text)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1770. Min Act: -0.1700

Data Index: 3611623 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1458. Min Act: -0.1700

Data Index: 1930747 (Open Web Text)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1770. Min Act: -0.1700

Data Index: 5599897 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1770. Min Act: -0.1700

Data Index: 8321785 (Open Web Text)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1145. Min Act: -0.1700

Data Index: 1263119 (Open Web Text)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.1145. Min Act: -0.1700

Data Index: 7747635 (Open Web Text)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0833. Min Act: -0.1700

Data Index: 1884440 (Open Web Text)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0833. Min Act: -0.1700

Data Index: 2101184 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0520. Min Act: -0.1700

Data Index: 981040 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0520. Min Act: -0.1700

Data Index: 1614797 (Open Web Text)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0520. Min Act: -0.1700

Data Index: 1253271 (Open Web Text)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0520. Min Act: -0.1700

Data Index: 6583741 (Open Web Text)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0208. Min Act: -0.1700

Data Index: 1909328 (Open Web Text)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0208. Min Act: -0.1700

Data Index: 6393675 (Open Web Text)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0208. Min Act: -0.1700

Data Index: 2093859 (Open Web Text)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.7083. Min Range: -6.7083

Max Act: 6.0208. Min Act: -0.1700

Data Index: 3914254 (Open Web Text)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #19