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

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

Neuron 1828 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0296. Min Act: -0.0006

Data Index: 593189 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1029401 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0271. Min Act: -0.0006

Data Index: 636389 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0262. Min Act: -0.0006

Data Index: 368225 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0253. Min Act: -0.0005

Data Index: 414742 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0257. Min Act: -0.0006

Data Index: 117592 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1229216 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0254. Min Act: -0.0005

Data Index: 241961 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0257. Min Act: -0.0006

Data Index: 722857 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1022026 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0251. Min Act: -0.0006

Data Index: 1079485 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1093155 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0248. Min Act: -0.0006

Data Index: 972547 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0254. Min Act: -0.0006

Data Index: 859073 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0247. Min Act: -0.0006

Data Index: 999070 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0246. Min Act: -0.0006

Data Index: 690048 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0250. Min Act: -0.0006

Data Index: 756048 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0245. Min Act: -0.0006

Data Index: 832756 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1179058 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1165948 (C4 (Web Text))

Max Activating Token Index: 67