Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 55 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1164364 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0256. Min Act: -0.0005

Data Index: 1135723 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0266. Min Act: -0.0005

Data Index: 642040 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0230. Min Act: -0.0005

Data Index: 698061 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0235. Min Act: -0.0005

Data Index: 621846 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0247. Min Act: -0.0005

Data Index: 772150 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0251. Min Act: -0.0005

Data Index: 870668 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0244. Min Act: -0.0005

Data Index: 942306 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0244. Min Act: -0.0005

Data Index: 843720 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0230. Min Act: -0.0005

Data Index: 717057 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0228. Min Act: -0.0005

Data Index: 1245478 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1198376 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0242. Min Act: -0.0005

Data Index: 702845 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0221. Min Act: -0.0005

Data Index: 551269 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0205. Min Act: -0.0005

Data Index: 857684 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0240. Min Act: -0.0005

Data Index: 962835 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0254. Min Act: -0.0005

Data Index: 1201214 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0235. Min Act: -0.0005

Data Index: 1119367 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0256. Min Act: -0.0005

Data Index: 1019450 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.0298. Min Range: -0.0298

Max Act: 0.0217. Min Act: -0.0005

Data Index: 604220 (C4 (Web Text))

Max Activating Token Index: 829