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

Dataset: Open Web Text

Neuron 2267 in Layer 3

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: 2.5323. Min Range: -2.5323

Max Act: 2.5323. Min Act: -0.1700

Data Index: 4235463 (Open Web Text)

Max Activating Token Index: 742

Text #1

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4719. Min Act: -0.1700

Data Index: 6135526 (Open Web Text)

Max Activating Token Index: 294

Text #2

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4578. Min Act: -0.1700

Data Index: 4098797 (Open Web Text)

Max Activating Token Index: 322

Text #3

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4379. Min Act: -0.1700

Data Index: 8505842 (Open Web Text)

Max Activating Token Index: 792

Text #4

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4599. Min Act: -0.1700

Data Index: 1431670 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4289. Min Act: -0.1700

Data Index: 8527336 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4391. Min Act: -0.1700

Data Index: 4555150 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4338. Min Act: -0.1700

Data Index: 7848875 (Open Web Text)

Max Activating Token Index: 471

Text #8

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4114. Min Act: -0.1700

Data Index: 5609022 (Open Web Text)

Max Activating Token Index: 436

Text #9

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4208. Min Act: -0.1700

Data Index: 732877 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4227. Min Act: -0.1700

Data Index: 2928339 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4202. Min Act: -0.1700

Data Index: 893190 (Open Web Text)

Max Activating Token Index: 863

Text #12

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4195. Min Act: -0.1700

Data Index: 6293566 (Open Web Text)

Max Activating Token Index: 681

Text #13

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.3913. Min Act: -0.1700

Data Index: 217982 (Open Web Text)

Max Activating Token Index: 577

Text #14

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.3981. Min Act: -0.1700

Data Index: 4793703 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.3973. Min Act: -0.1700

Data Index: 576400 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4000. Min Act: -0.1700

Data Index: 565417 (Open Web Text)

Max Activating Token Index: 305

Text #17

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4053. Min Act: -0.1700

Data Index: 7217843 (Open Web Text)

Max Activating Token Index: 899

Text #18

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.4060. Min Act: -0.1700

Data Index: 6609932 (Open Web Text)

Max Activating Token Index: 866

Text #19

Max Range: 2.5323. Min Range: -2.5323

Max Act: 2.3931. Min Act: -0.1700

Data Index: 1384990 (Open Web Text)

Max Activating Token Index: 355