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

Dataset: Open Web Text

Neuron 2984 in Layer 0

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: 1.3411. Min Range: -1.3411

Max Act: 1.3411. Min Act: -0.1552

Data Index: 8370189 (Open Web Text)

Max Activating Token Index: 1006

Text #1

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3295. Min Act: -0.1552

Data Index: 1289182 (Open Web Text)

Max Activating Token Index: 278

Text #2

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3237. Min Act: -0.1552

Data Index: 849309 (Open Web Text)

Max Activating Token Index: 164

Text #3

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3128. Min Act: -0.1552

Data Index: 1253484 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3136. Min Act: -0.1552

Data Index: 3259267 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3155. Min Act: -0.1552

Data Index: 7810 (Open Web Text)

Max Activating Token Index: 667

Text #6

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3129. Min Act: -0.1552

Data Index: 1564643 (Open Web Text)

Max Activating Token Index: 408

Text #7

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3140. Min Act: -0.1552

Data Index: 8215930 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3166. Min Act: -0.1552

Data Index: 4132541 (Open Web Text)

Max Activating Token Index: 134

Text #9

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3142. Min Act: -0.1552

Data Index: 4444732 (Open Web Text)

Max Activating Token Index: 135

Text #10

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3136. Min Act: -0.1552

Data Index: 3475249 (Open Web Text)

Max Activating Token Index: 876

Text #11

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3009. Min Act: -0.1552

Data Index: 2389912 (Open Web Text)

Max Activating Token Index: 477

Text #12

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3071. Min Act: -0.1552

Data Index: 1253476 (Open Web Text)

Max Activating Token Index: 218

Text #13

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.3025. Min Act: -0.1552

Data Index: 4103711 (Open Web Text)

Max Activating Token Index: 184

Text #14

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2954. Min Act: -0.1552

Data Index: 4655739 (Open Web Text)

Max Activating Token Index: 59

Text #15

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2930. Min Act: -0.1552

Data Index: 1253477 (Open Web Text)

Max Activating Token Index: 136

Text #16

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2977. Min Act: -0.1552

Data Index: 1253482 (Open Web Text)

Max Activating Token Index: 174

Text #17

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2971. Min Act: -0.1552

Data Index: 2988566 (Open Web Text)

Max Activating Token Index: 886

Text #18

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2966. Min Act: -0.1552

Data Index: 1253485 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 1.3411. Min Range: -1.3411

Max Act: 1.2988. Min Act: -0.1552

Data Index: 5692243 (Open Web Text)

Max Activating Token Index: 209