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

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

Neuron 788 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: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0006

Data Index: 289929 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1101152 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0225. Min Act: -0.0006

Data Index: 763997 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0223. Min Act: -0.0005

Data Index: 610080 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0227. Min Act: -0.0006

Data Index: 958514 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1280223 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0209. Min Act: -0.0006

Data Index: 892083 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0208. Min Act: -0.0006

Data Index: 1135280 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0204. Min Act: -0.0006

Data Index: 58151 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0194. Min Act: -0.0006

Data Index: 238300 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0193. Min Act: -0.0006

Data Index: 69458 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0191. Min Act: -0.0006

Data Index: 232344 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1293803 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0198. Min Act: -0.0006

Data Index: 464276 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1306617 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0189. Min Act: -0.0006

Data Index: 376020 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0189. Min Act: -0.0006

Data Index: 1004085 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0197. Min Act: -0.0006

Data Index: 615522 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0190. Min Act: -0.0006

Data Index: 361467 (C4 (Web Text))

Max Activating Token Index: 862