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

Dataset: Open Web Text

Neuron 576 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: 4.4407. Min Range: -4.4407

Max Act: 4.4407. Min Act: -0.1700

Data Index: 17448 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.3269. Min Act: -0.1700

Data Index: 6867688 (Open Web Text)

Max Activating Token Index: 316

Text #2

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.3200. Min Act: -0.1700

Data Index: 6524701 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.3051. Min Act: -0.1700

Data Index: 1252613 (Open Web Text)

Max Activating Token Index: 452

Text #4

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.2537. Min Act: -0.1700

Data Index: 6506268 (Open Web Text)

Max Activating Token Index: 264

Text #5

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.2342. Min Act: -0.1700

Data Index: 1092775 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1977. Min Act: -0.1700

Data Index: 5118763 (Open Web Text)

Max Activating Token Index: 342

Text #7

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1967. Min Act: -0.1700

Data Index: 8132312 (Open Web Text)

Max Activating Token Index: 1018

Text #8

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1742. Min Act: -0.1700

Data Index: 8248853 (Open Web Text)

Max Activating Token Index: 161

Text #9

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.2036. Min Act: -0.1700

Data Index: 4070793 (Open Web Text)

Max Activating Token Index: 159

Text #10

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1731. Min Act: -0.1700

Data Index: 3006084 (Open Web Text)

Max Activating Token Index: 212

Text #11

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1975. Min Act: -0.1700

Data Index: 4979081 (Open Web Text)

Max Activating Token Index: 368

Text #12

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.2083. Min Act: -0.1700

Data Index: 4796419 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1474. Min Act: -0.1700

Data Index: 2300175 (Open Web Text)

Max Activating Token Index: 267

Text #14

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1283. Min Act: -0.1700

Data Index: 6855990 (Open Web Text)

Max Activating Token Index: 233

Text #15

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1286. Min Act: -0.1700

Data Index: 4312289 (Open Web Text)

Max Activating Token Index: 825

Text #16

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1008. Min Act: -0.1700

Data Index: 972567 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1195. Min Act: -0.1700

Data Index: 2367061 (Open Web Text)

Max Activating Token Index: 318

Text #18

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1117. Min Act: -0.1700

Data Index: 3128301 (Open Web Text)

Max Activating Token Index: 218

Text #19

Max Range: 4.4407. Min Range: -4.4407

Max Act: 4.1079. Min Act: -0.1700

Data Index: 6270509 (Open Web Text)

Max Activating Token Index: 174