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

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

Neuron 4957 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: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0002

Data Index: 14244 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1224881 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0320. Min Act: -0.0002

Data Index: 298404 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1331756 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0319. Min Act: -0.0002

Data Index: 29772 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1233783 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0309. Min Act: -0.0002

Data Index: 697018 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1053424 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0291. Min Act: -0.0002

Data Index: 599980 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0288. Min Act: -0.0002

Data Index: 775314 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0253. Min Act: -0.0002

Data Index: 343468 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0260. Min Act: -0.0002

Data Index: 61665 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0271. Min Act: -0.0002

Data Index: 379383 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1319700 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0274. Min Act: -0.0002

Data Index: 871180 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0262. Min Act: -0.0002

Data Index: 936173 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1055886 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0245. Min Act: -0.0002

Data Index: 352093 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1232705 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0267. Min Act: -0.0002

Data Index: 918733 (C4 (Web Text))

Max Activating Token Index: 8