Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0002

Data Index: 576387 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0297. Min Act: -0.0002

Data Index: 972461 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0290. Min Act: -0.0002

Data Index: 524037 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0274. Min Act: -0.0002

Data Index: 831764 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0284. Min Act: -0.0002

Data Index: 341230 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0304. Min Act: -0.0002

Data Index: 886713 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0271. Min Act: -0.0002

Data Index: 525591 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0282. Min Act: -0.0002

Data Index: 652412 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0258. Min Act: -0.0002

Data Index: 272428 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0268. Min Act: -0.0002

Data Index: 732133 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0292. Min Act: -0.0002

Data Index: 598638 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0260. Min Act: -0.0002

Data Index: 836616 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0241. Min Act: -0.0002

Data Index: 735422 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0271. Min Act: -0.0002

Data Index: 408215 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0278. Min Act: -0.0002

Data Index: 199721 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0263. Min Act: -0.0002

Data Index: 201420 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0244. Min Act: -0.0002

Data Index: 915043 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0272. Min Act: -0.0002

Data Index: 759988 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0260. Min Act: -0.0002

Data Index: 325755 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0256. Min Act: -0.0002

Data Index: 983438 (C4 (Web Text))

Max Activating Token Index: 21