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

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

Neuron 906 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: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0006

Data Index: 50683 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0259. Min Act: -0.0006

Data Index: 882804 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0254. Min Act: -0.0006

Data Index: 213436 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0006

Data Index: 670139 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0240. Min Act: -0.0006

Data Index: 928427 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1035263 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0006

Data Index: 380214 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1059624 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0236. Min Act: -0.0006

Data Index: 885671 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0234. Min Act: -0.0006

Data Index: 39801 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0006

Data Index: 323225 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0231. Min Act: -0.0006

Data Index: 956180 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0226. Min Act: -0.0006

Data Index: 374765 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0231. Min Act: -0.0006

Data Index: 68805 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0224. Min Act: -0.0006

Data Index: 485790 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0223. Min Act: -0.0006

Data Index: 605117 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0228. Min Act: -0.0006

Data Index: 636953 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0227. Min Act: -0.0006

Data Index: 324049 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1077243 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0225. Min Act: -0.0006

Data Index: 242391 (C4 (Web Text))

Max Activating Token Index: 786