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

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

Neuron 3871 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1224970 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.8736. Min Act: -0.0000

Data Index: 254684 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.7936. Min Act: -0.0000

Data Index: 715967 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.7047. Min Act: -0.0000

Data Index: 364532 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1195763 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6360. Min Act: -0.0000

Data Index: 608035 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6255. Min Act: -0.0000

Data Index: 200611 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6463. Min Act: -0.0000

Data Index: 684212 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6367. Min Act: -0.0000

Data Index: 306775 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.6351. Min Act: -0.0000

Data Index: 486521 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1499272 (Python Code)

Max Activating Token Index: 838

Text #11

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5878. Min Act: -0.0000

Data Index: 918426 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5863. Min Act: -0.0000

Data Index: 905699 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5974. Min Act: -0.0000

Data Index: 792810 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5957. Min Act: -0.0000

Data Index: 772860 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1494086 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1193659 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5376. Min Act: -0.0000

Data Index: 352511 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5566. Min Act: -0.0000

Data Index: 983992 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.8923. Min Range: -0.8923

Max Act: 0.5226. Min Act: -0.0000

Data Index: 77424 (C4 (Web Text))

Max Activating Token Index: 694