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

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

Neuron 1573 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: 0.0238. Min Range: -0.0238

Max Act: 0.0238. Min Act: -0.0006

Data Index: 290120 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1184089 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0206. Min Act: -0.0006

Data Index: 1344992 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0215. Min Act: -0.0006

Data Index: 49585 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1194667 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1220923 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1146119 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0204. Min Act: -0.0006

Data Index: 890343 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1352619 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0204. Min Act: -0.0006

Data Index: 381252 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0204. Min Act: -0.0006

Data Index: 39620 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0205. Min Act: -0.0006

Data Index: 1240839 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0006

Data Index: 469008 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0195. Min Act: -0.0006

Data Index: 600777 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0197. Min Act: -0.0006

Data Index: 384953 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1150394 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1250325 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1251011 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0197. Min Act: -0.0006

Data Index: 245594 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0238. Min Range: -0.0238

Max Act: 0.0188. Min Act: -0.0006

Data Index: 898225 (C4 (Web Text))

Max Activating Token Index: 141