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

Dataset: Open Web Text

Neuron 2693 in Layer 1

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: 0.7278. Min Range: -0.7278

Max Act: 0.7278. Min Act: -0.1700

Data Index: 5206153 (Open Web Text)

Max Activating Token Index: 360

Text #1

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7239. Min Act: -0.1700

Data Index: 8344446 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7215. Min Act: -0.1700

Data Index: 7618251 (Open Web Text)

Max Activating Token Index: 363

Text #3

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7156. Min Act: -0.1700

Data Index: 6892001 (Open Web Text)

Max Activating Token Index: 366

Text #4

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7174. Min Act: -0.1700

Data Index: 760089 (Open Web Text)

Max Activating Token Index: 371

Text #5

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7125. Min Act: -0.1700

Data Index: 2743903 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7124. Min Act: -0.1700

Data Index: 8709539 (Open Web Text)

Max Activating Token Index: 377

Text #7

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7141. Min Act: -0.1700

Data Index: 434084 (Open Web Text)

Max Activating Token Index: 377

Text #8

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7054. Min Act: -0.1700

Data Index: 7347404 (Open Web Text)

Max Activating Token Index: 384

Text #9

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7109. Min Act: -0.1700

Data Index: 2858559 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7133. Min Act: -0.1700

Data Index: 7131901 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7043. Min Act: -0.1700

Data Index: 5108772 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7049. Min Act: -0.1700

Data Index: 4889872 (Open Web Text)

Max Activating Token Index: 351

Text #13

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7098. Min Act: -0.1700

Data Index: 4727134 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7096. Min Act: -0.1700

Data Index: 4578044 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6994. Min Act: -0.1700

Data Index: 4159435 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7043. Min Act: -0.1700

Data Index: 476289 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6989. Min Act: -0.1700

Data Index: 483145 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6958. Min Act: -0.1700

Data Index: 2275512 (Open Web Text)

Max Activating Token Index: 390

Text #19

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7017. Min Act: -0.1700

Data Index: 4555722 (Open Web Text)

Max Activating Token Index: 395