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

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

Neuron 590 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2426. Min Range: -2.2426

Max Act: 2.2426. Min Act: -0.0000

Data Index: 489626 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 2.2426. Min Range: -2.2426

Max Act: 2.0507. Min Act: -0.0000

Data Index: 282556 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 2.2426. Min Range: -2.2426

Max Act: 2.1185. Min Act: -0.0000

Data Index: 702684 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.8254. Min Act: -0.0000

Data Index: 690213 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.9175. Min Act: -0.0000

Data Index: 1010482 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.9738. Min Act: -0.0000

Data Index: 195429 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7710. Min Act: -0.0000

Data Index: 1271017 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.5615. Min Act: -0.0000

Data Index: 926597 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6531. Min Act: -0.0000

Data Index: 931347 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6434. Min Act: -0.0000

Data Index: 796262 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6359. Min Act: -0.0000

Data Index: 988380 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6294. Min Act: -0.0000

Data Index: 22682 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7080. Min Act: -0.0000

Data Index: 468373 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7016. Min Act: -0.0000

Data Index: 449515 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.7802. Min Act: -0.0000

Data Index: 533514 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6784. Min Act: -0.0000

Data Index: 521584 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1175631 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6655. Min Act: -0.0000

Data Index: 403596 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6599. Min Act: -0.0000

Data Index: 1326637 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 2.2426. Min Range: -2.2426

Max Act: 1.6573. Min Act: -0.0000

Data Index: 750543 (C4 (Web Text))

Max Activating Token Index: 549