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

Dataset: The Pile

Neuron 4269 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1704404 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0326. Min Act: -0.0000

Data Index: 476673 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1822051 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1225212 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1635986 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0318. Min Act: -0.0000

Data Index: 865592 (The Pile)

Max Activating Token Index: 48

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1635565 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1141292 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1915821 (The Pile)

Max Activating Token Index: 77

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1632034 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0317. Min Act: -0.0000

Data Index: 36295 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0315. Min Act: -0.0000

Data Index: 400332 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1870058 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0314. Min Act: -0.0000

Data Index: 552322 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0322. Min Act: -0.0000

Data Index: 1869411 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1539815 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0310. Min Act: -0.0000

Data Index: 834001 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0309. Min Act: -0.0000

Data Index: 791321 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1042740 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0307. Min Act: -0.0000

Data Index: 203256 (The Pile)

Max Activating Token Index: 201