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

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

Neuron 3365 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0000

Data Index: 393051 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0509. Min Act: -0.0000

Data Index: 127593 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0411. Min Act: -0.0000

Data Index: 173036 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0351. Min Act: -0.0000

Data Index: 212625 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0440. Min Act: -0.0001

Data Index: 166810 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0395. Min Act: -0.0000

Data Index: 148403 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0393. Min Act: -0.0000

Data Index: 791905 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1170559 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0377. Min Act: -0.0000

Data Index: 260750 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1157649 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0386. Min Act: -0.0000

Data Index: 293845 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0383. Min Act: -0.0000

Data Index: 88816 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1336558 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0406. Min Act: -0.0000

Data Index: 170903 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0361. Min Act: -0.0000

Data Index: 483576 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0399. Min Act: -0.0000

Data Index: 864894 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1022366 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0373. Min Act: -0.0000

Data Index: 443902 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0343. Min Act: -0.0000

Data Index: 392482 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0361. Min Act: -0.0000

Data Index: 545914 (C4 (Web Text))

Max Activating Token Index: 263