Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3228 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1357440 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1410479 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0280. Min Act: -0.0002

Data Index: 484996 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1212154 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1403078 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1573308 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1645450 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0252. Min Act: -0.0002

Data Index: 342059 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0234. Min Act: -0.0002

Data Index: 598224 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1423162 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1370565 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1646376 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1626927 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1564196 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1606385 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0228. Min Act: -0.0002

Data Index: 487665 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0229. Min Act: -0.0002

Data Index: 143772 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0217. Min Act: -0.0002

Data Index: 421907 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1577030 (Python Code)

Max Activating Token Index: 184

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1439487 (Python Code)

Max Activating Token Index: 224