Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 736 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.6162. Min Act: -0.1700

Data Index: 7008093 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.5173. Min Act: -0.1700

Data Index: 6180309 (Open Web Text)

Max Activating Token Index: 697

Text #2

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.5087. Min Act: -0.1700

Data Index: 6435374 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4875. Min Act: -0.1700

Data Index: 7826096 (Open Web Text)

Max Activating Token Index: 239

Text #4

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4626. Min Act: -0.1700

Data Index: 7982943 (Open Web Text)

Max Activating Token Index: 486

Text #5

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4673. Min Act: -0.1700

Data Index: 2176499 (Open Web Text)

Max Activating Token Index: 900

Text #6

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4353. Min Act: -0.1700

Data Index: 1665075 (Open Web Text)

Max Activating Token Index: 881

Text #7

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4383. Min Act: -0.1700

Data Index: 7330270 (Open Web Text)

Max Activating Token Index: 940

Text #8

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4188. Min Act: -0.1700

Data Index: 8560358 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4009. Min Act: -0.1700

Data Index: 4852867 (Open Web Text)

Max Activating Token Index: 447

Text #10

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.4227. Min Act: -0.1700

Data Index: 5972486 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3953. Min Act: -0.1700

Data Index: 3195932 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3971. Min Act: -0.1700

Data Index: 6659048 (Open Web Text)

Max Activating Token Index: 927

Text #13

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3724. Min Act: -0.1700

Data Index: 2132426 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3705. Min Act: -0.1700

Data Index: 315041 (Open Web Text)

Max Activating Token Index: 350

Text #15

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3638. Min Act: -0.1700

Data Index: 599758 (Open Web Text)

Max Activating Token Index: 962

Text #16

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3791. Min Act: -0.1700

Data Index: 6505089 (Open Web Text)

Max Activating Token Index: 271

Text #17

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3617. Min Act: -0.1700

Data Index: 5400092 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3510. Min Act: -0.1700

Data Index: 1905014 (Open Web Text)

Max Activating Token Index: 452

Text #19

Max Range: 3.6162. Min Range: -3.6162

Max Act: 3.3635. Min Act: -0.1700

Data Index: 5453229 (Open Web Text)

Max Activating Token Index: 438