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

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

Neuron 4040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: 0.0000

Data Index: 420280 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0306. Min Act: -0.0000

Data Index: 46969 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0312. Min Act: 0.0000

Data Index: 963187 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0254. Min Act: -0.0000

Data Index: 874092 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0241. Min Act: -0.0000

Data Index: 754423 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0240. Min Act: 0.0001

Data Index: 933584 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0222. Min Act: 0.0001

Data Index: 823222 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0221. Min Act: 0.0001

Data Index: 858371 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0236. Min Act: 0.0000

Data Index: 1152247 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0219. Min Act: 0.0001

Data Index: 260384 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0215. Min Act: -0.0000

Data Index: 469580 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0223. Min Act: 0.0001

Data Index: 183459 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0251. Min Act: 0.0000

Data Index: 119547 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0198. Min Act: -0.0000

Data Index: 56180 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0228. Min Act: 0.0001

Data Index: 143958 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0223. Min Act: -0.0000

Data Index: 603630 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0219. Min Act: -0.0000

Data Index: 761879 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0223. Min Act: 0.0000

Data Index: 920798 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0217. Min Act: -0.0000

Data Index: 882770 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0206. Min Act: 0.0000

Data Index: 300467 (C4 (Web Text))

Max Activating Token Index: 20