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

Dataset: Open Web Text

Neuron 2222 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: 3.6316. Min Range: -3.6316

Max Act: 3.6211. Min Act: -0.1700

Data Index: 7757851 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.6277. Min Act: -0.1700

Data Index: 176233 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.6316. Min Act: -0.1700

Data Index: 2140817 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5765. Min Act: -0.1700

Data Index: 1882645 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5846. Min Act: -0.1700

Data Index: 6260870 (Open Web Text)

Max Activating Token Index: 219

Text #5

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5835. Min Act: -0.1700

Data Index: 5173925 (Open Web Text)

Max Activating Token Index: 420

Text #6

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5170. Min Act: -0.1700

Data Index: 455837 (Open Web Text)

Max Activating Token Index: 530

Text #7

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5219. Min Act: -0.1700

Data Index: 5837772 (Open Web Text)

Max Activating Token Index: 684

Text #8

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5498. Min Act: -0.1700

Data Index: 7069238 (Open Web Text)

Max Activating Token Index: 442

Text #9

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5246. Min Act: -0.1700

Data Index: 4908831 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5027. Min Act: -0.1700

Data Index: 1650194 (Open Web Text)

Max Activating Token Index: 191

Text #11

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.4997. Min Act: -0.1700

Data Index: 965717 (Open Web Text)

Max Activating Token Index: 211

Text #12

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5179. Min Act: -0.1700

Data Index: 3947945 (Open Web Text)

Max Activating Token Index: 1007

Text #13

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5092. Min Act: -0.1700

Data Index: 3113441 (Open Web Text)

Max Activating Token Index: 484

Text #14

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.4847. Min Act: -0.1700

Data Index: 5962384 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5106. Min Act: -0.1700

Data Index: 3233427 (Open Web Text)

Max Activating Token Index: 962

Text #16

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.4928. Min Act: -0.1700

Data Index: 4018182 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.4949. Min Act: -0.1700

Data Index: 4165678 (Open Web Text)

Max Activating Token Index: 650

Text #18

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5019. Min Act: -0.1700

Data Index: 690394 (Open Web Text)

Max Activating Token Index: 567

Text #19

Max Range: 3.6316. Min Range: -3.6316

Max Act: 3.5227. Min Act: -0.1700

Data Index: 4310551 (Open Web Text)

Max Activating Token Index: 134