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

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

Neuron 1682 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: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1522157 (Python Code)

Max Activating Token Index: 159

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0303. Min Act: -0.0002

Data Index: 239330 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0275. Min Act: -0.0002

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1598105 (Python Code)

Max Activating Token Index: 109

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1616937 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1151273 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1576782 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1389878 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1451619 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1449984 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1477797 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1606133 (Python Code)

Max Activating Token Index: 120

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1580631 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0236. Min Act: -0.0002

Data Index: 371421 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0224. Min Act: -0.0002

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1575286 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1454456 (Python Code)

Max Activating Token Index: 129

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1470192 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1561615 (Python Code)

Max Activating Token Index: 103