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

Dataset: Open Web Text

Neuron 42 in Layer 2

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: 4.7530. Min Range: -4.7530

Max Act: 4.7530. Min Act: -0.1700

Data Index: 5312686 (Open Web Text)

Max Activating Token Index: 160

Text #1

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.7169. Min Act: -0.1700

Data Index: 247929 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.7348. Min Act: -0.1700

Data Index: 5594196 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.6475. Min Act: -0.1700

Data Index: 2044710 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.6475. Min Act: -0.1700

Data Index: 7279456 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.6299. Min Act: -0.1700

Data Index: 2037389 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.5676. Min Act: -0.1700

Data Index: 6515936 (Open Web Text)

Max Activating Token Index: 473

Text #7

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.5652. Min Act: -0.1700

Data Index: 5971094 (Open Web Text)

Max Activating Token Index: 98

Text #8

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.5497. Min Act: -0.1700

Data Index: 2037384 (Open Web Text)

Max Activating Token Index: 258

Text #9

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.5401. Min Act: -0.1700

Data Index: 8548431 (Open Web Text)

Max Activating Token Index: 433

Text #10

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4850. Min Act: -0.1700

Data Index: 1655356 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4871. Min Act: -0.1700

Data Index: 5726562 (Open Web Text)

Max Activating Token Index: 92

Text #12

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4949. Min Act: -0.1700

Data Index: 5293212 (Open Web Text)

Max Activating Token Index: 435

Text #13

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4584. Min Act: -0.1700

Data Index: 2540148 (Open Web Text)

Max Activating Token Index: 441

Text #14

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4344. Min Act: -0.1700

Data Index: 4543799 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4152. Min Act: -0.1700

Data Index: 8113550 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4518. Min Act: -0.1700

Data Index: 4070517 (Open Web Text)

Max Activating Token Index: 410

Text #17

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.3966. Min Act: -0.1700

Data Index: 4615668 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.4177. Min Act: -0.1700

Data Index: 4871093 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 4.7530. Min Range: -4.7530

Max Act: 4.3914. Min Act: -0.1700

Data Index: 3859831 (Open Web Text)

Max Activating Token Index: 482