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

Dataset: The Pile

Neuron 1251 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1956763 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3137. Min Act: -0.0000

Data Index: 6590 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1660334 (The Pile)

Max Activating Token Index: 817

Text #3

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1982146 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.3294. Min Act: -0.0000

Data Index: 430202 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1764281 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2689. Min Act: -0.0000

Data Index: 122147 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2849. Min Act: -0.0000

Data Index: 582479 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2555. Min Act: -0.0000

Data Index: 622299 (The Pile)

Max Activating Token Index: 879

Text #9

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1390408 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2669. Min Act: -0.0000

Data Index: 400361 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1143428 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1975255 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1268843 (The Pile)

Max Activating Token Index: 928

Text #14

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1998174 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1483819 (The Pile)

Max Activating Token Index: 372

Text #16

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2461. Min Act: -0.0000

Data Index: 312557 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1996393 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1453444 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 0.4205. Min Range: -0.4205

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1971614 (The Pile)

Max Activating Token Index: 865