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

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

Neuron 1124 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0270. Min Act: -0.0006

Data Index: 1265003 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1357000 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0283. Min Act: -0.0006

Data Index: 928834 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0281. Min Act: -0.0006

Data Index: 228011 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0246. Min Act: -0.0006

Data Index: 945004 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1174551 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0243. Min Act: -0.0006

Data Index: 145639 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0261. Min Act: -0.0006

Data Index: 18225 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0233. Min Act: -0.0006

Data Index: 757273 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0233. Min Act: -0.0006

Data Index: 624241 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0248. Min Act: -0.0006

Data Index: 251485 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1349343 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1166097 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0248. Min Act: -0.0006

Data Index: 774169 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0225. Min Act: -0.0006

Data Index: 963987 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0255. Min Act: -0.0006

Data Index: 782426 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0228. Min Act: -0.0006

Data Index: 720881 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0232. Min Act: -0.0006

Data Index: 496323 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0220. Min Act: -0.0006

Data Index: 931491 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0233. Min Act: -0.0006

Data Index: 1249263 (C4 (Web Text))

Max Activating Token Index: 587