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

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

Neuron 913 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: 0.0274. Min Act: -0.0006

Data Index: 846509 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0274. Min Act: -0.0006

Data Index: 198733 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0270. Min Act: -0.0006

Data Index: 289216 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0276. Min Act: -0.0006

Data Index: 63660 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0261. Min Act: -0.0006

Data Index: 232532 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0261. Min Act: -0.0006

Data Index: 408680 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1585845 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1139190 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0244. Min Act: -0.0005

Data Index: 435543 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1498433 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0248. Min Act: -0.0006

Data Index: 976196 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0239. Min Act: -0.0006

Data Index: 973333 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1575426 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0232. Min Act: -0.0005

Data Index: 1199202 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0242. Min Act: -0.0006

Data Index: 833742 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0237. Min Act: -0.0006

Data Index: 1191255 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0241. Min Act: -0.0006

Data Index: 1360656 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0230. Min Act: -0.0005

Data Index: 1218126 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0234. Min Act: -0.0006

Data Index: 670262 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1334155 (C4 (Web Text))

Max Activating Token Index: 485