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

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

Neuron 3165 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1601915 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9969. Min Act: -0.0000

Data Index: 58049 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1519351 (Python Code)

Max Activating Token Index: 793

Text #3

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1222608 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1636915 (Python Code)

Max Activating Token Index: 77

Text #5

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1532399 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1407633 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1364227 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8689. Min Act: -0.0000

Data Index: 651309 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8518. Min Act: -0.0000

Data Index: 520398 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1610384 (Python Code)

Max Activating Token Index: 906

Text #11

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1472637 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8374. Min Act: -0.0000

Data Index: 26858 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8006. Min Act: -0.0000

Data Index: 173640 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8394. Min Act: -0.0000

Data Index: 352108 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1507635 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7904. Min Act: -0.0000

Data Index: 431752 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1505893 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1377732 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7927. Min Act: -0.0000

Data Index: 952496 (C4 (Web Text))

Max Activating Token Index: 782