Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2731 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.4138. Min Act: -0.0000

Data Index: 1137166 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3576. Min Act: -0.0000

Data Index: 237367 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3125. Min Act: -0.0000

Data Index: 976885 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3196. Min Act: -0.0000

Data Index: 195136 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3475. Min Act: -0.0000

Data Index: 395019 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3232. Min Act: -0.0000

Data Index: 293111 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1071517 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3316. Min Act: -0.0000

Data Index: 99828 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2994. Min Act: -0.0000

Data Index: 267582 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1317645 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3245. Min Act: -0.0000

Data Index: 650872 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3186. Min Act: -0.0000

Data Index: 526661 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1353629 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1098054 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3052. Min Act: -0.0000

Data Index: 908536 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3010. Min Act: -0.0000

Data Index: 951000 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1180294 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1178465 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.3468. Min Act: -0.0000

Data Index: 179593 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.4138. Min Range: -0.4138

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1098770 (C4 (Web Text))

Max Activating Token Index: 423