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

Dataset: The Pile

Neuron 2442 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1910439 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1993707 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1908310 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3925. Min Act: -0.0000

Data Index: 321049 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1652173 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3722. Min Act: -0.0000

Data Index: 671349 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1524535 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1650836 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1886316 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3543. Min Act: -0.0000

Data Index: 756859 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3453. Min Act: -0.0000

Data Index: 259547 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1640108 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1617874 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1194172 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1874206 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1156855 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3438. Min Act: -0.0000

Data Index: 15659 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1892954 (The Pile)

Max Activating Token Index: 905

Text #18

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1642014 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3034. Min Act: -0.0000

Data Index: 368385 (The Pile)

Max Activating Token Index: 200