Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 471 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3323. Min Act: -0.0001

Data Index: 140830 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3279. Min Act: -0.0001

Data Index: 917086 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2996. Min Act: -0.0001

Data Index: 921334 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2889. Min Act: -0.0001

Data Index: 380228 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2594. Min Act: -0.0001

Data Index: 1275302 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2253. Min Act: -0.0001

Data Index: 120936 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2628. Min Act: -0.0001

Data Index: 1052571 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2714. Min Act: -0.0001

Data Index: 322896 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2574. Min Act: -0.0001

Data Index: 909126 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2392. Min Act: -0.0001

Data Index: 921626 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2309. Min Act: -0.0001

Data Index: 574731 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2187. Min Act: -0.0001

Data Index: 237179 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2214. Min Act: -0.0001

Data Index: 409346 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2249. Min Act: -0.0001

Data Index: 834415 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2245. Min Act: -0.0001

Data Index: 852215 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1114302 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2266. Min Act: -0.0000

Data Index: 827324 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2269. Min Act: -0.0001

Data Index: 752894 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2167. Min Act: -0.0001

Data Index: 487895 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2158. Min Act: -0.0001

Data Index: 65056 (C4 (Web Text))

Max Activating Token Index: 899