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

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

Neuron 469 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: 0.0276. Min Range: -0.0276

Max Act: 0.0276. Min Act: -0.0006

Data Index: 725303 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1123472 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0227. Min Act: -0.0006

Data Index: 348392 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0230. Min Act: -0.0006

Data Index: 564188 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1310064 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1308793 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0218. Min Act: -0.0006

Data Index: 757846 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1306300 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0222. Min Act: -0.0006

Data Index: 953182 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0207. Min Act: -0.0006

Data Index: 375574 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0212. Min Act: -0.0006

Data Index: 179827 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0220. Min Act: -0.0006

Data Index: 209998 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0215. Min Act: -0.0006

Data Index: 618140 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0197. Min Act: -0.0006

Data Index: 647462 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0209. Min Act: -0.0006

Data Index: 992076 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0214. Min Act: -0.0006

Data Index: 814239 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0202. Min Act: -0.0006

Data Index: 1103911 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0208. Min Act: -0.0006

Data Index: 70575 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0203. Min Act: -0.0006

Data Index: 680970 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0202. Min Act: -0.0006

Data Index: 267768 (C4 (Web Text))

Max Activating Token Index: 45