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

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

Neuron 5807 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1080371 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.4182. Min Act: -0.0000

Data Index: 560012 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3966. Min Act: -0.0000

Data Index: 429066 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3777. Min Act: -0.0000

Data Index: 433995 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3594. Min Act: -0.0000

Data Index: 420701 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1123493 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3156. Min Act: -0.0000

Data Index: 877372 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3439. Min Act: -0.0000

Data Index: 60802 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3471. Min Act: -0.0001

Data Index: 154164 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3284. Min Act: -0.0000

Data Index: 370754 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3251. Min Act: -0.0000

Data Index: 9825 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3413. Min Act: -0.0000

Data Index: 323785 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.2990. Min Act: -0.0000

Data Index: 505451 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3154. Min Act: -0.0000

Data Index: 442834 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3166. Min Act: -0.0000

Data Index: 79537 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1345140 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3025. Min Act: -0.0000

Data Index: 409777 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1270014 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3303. Min Act: -0.0000

Data Index: 535712 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.4501. Min Range: -0.4501

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1178891 (C4 (Web Text))

Max Activating Token Index: 550