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

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

Neuron 266 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: 0.0261. Min Range: -0.0261

Max Act: 0.0261. Min Act: -0.0006

Data Index: 428485 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0248. Min Act: -0.0006

Data Index: 884014 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1096683 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1139540 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0226. Min Act: -0.0006

Data Index: 840837 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0223. Min Act: -0.0006

Data Index: 564102 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0212. Min Act: -0.0006

Data Index: 141669 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0212. Min Act: -0.0006

Data Index: 526230 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0199. Min Act: -0.0006

Data Index: 185549 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0200. Min Act: -0.0006

Data Index: 280717 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0199. Min Act: -0.0006

Data Index: 747020 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0210. Min Act: -0.0006

Data Index: 258994 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0204. Min Act: -0.0006

Data Index: 199244 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0191. Min Act: -0.0006

Data Index: 898103 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1214330 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0208. Min Act: -0.0006

Data Index: 27223 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0202. Min Act: -0.0006

Data Index: 429805 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0204. Min Act: -0.0006

Data Index: 1093752 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0198. Min Act: -0.0006

Data Index: 715544 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0206. Min Act: -0.0006

Data Index: 380233 (C4 (Web Text))

Max Activating Token Index: 920