Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1813 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0006

Data Index: 368903 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0193. Min Act: -0.0006

Data Index: 893616 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0191. Min Act: -0.0006

Data Index: 323756 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0192. Min Act: -0.0006

Data Index: 761408 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0189. Min Act: -0.0006

Data Index: 703974 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0196. Min Act: -0.0006

Data Index: 583881 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0191. Min Act: -0.0006

Data Index: 298917 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0188. Min Act: -0.0006

Data Index: 625753 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0186. Min Act: -0.0006

Data Index: 721582 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0181. Min Act: -0.0006

Data Index: 511128 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0184. Min Act: -0.0006

Data Index: 157384 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0180. Min Act: -0.0005

Data Index: 1242499 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0189. Min Act: -0.0006

Data Index: 266300 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0180. Min Act: -0.0006

Data Index: 128249 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0176. Min Act: -0.0006

Data Index: 515054 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1176796 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0186. Min Act: -0.0006

Data Index: 166164 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0175. Min Act: -0.0006

Data Index: 580024 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0178. Min Act: -0.0006

Data Index: 834323 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0174. Min Act: -0.0006

Data Index: 703062 (C4 (Web Text))

Max Activating Token Index: 290