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

Dataset: The Pile

Neuron 3651 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3414. Min Act: -0.0000

Data Index: 400085 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.7345. Min Act: -0.0000

Data Index: 431992 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.6205. Min Act: -0.0000

Data Index: 1727299 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.5980. Min Act: -0.0000

Data Index: 1957342 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.5533. Min Act: -0.0000

Data Index: 751903 (The Pile)

Max Activating Token Index: 347

Text #5

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1743960 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.4209. Min Act: -0.0000

Data Index: 393169 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1447657 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3933. Min Act: -0.0000

Data Index: 1602305 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3541. Min Act: -0.0000

Data Index: 509065 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3448. Min Act: -0.0000

Data Index: 328241 (The Pile)

Max Activating Token Index: 188

Text #11

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3468. Min Act: 0.0000

Data Index: 582311 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1729458 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.3502. Min Act: 0.0000

Data Index: 114289 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.2898. Min Act: -0.0000

Data Index: 471552 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.5133. Min Act: 0.0000

Data Index: 1365431 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1905092 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.2966. Min Act: -0.0000

Data Index: 1479578 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.2508. Min Act: -0.0000

Data Index: 356218 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 1.7345. Min Range: -1.7345

Max Act: 1.2456. Min Act: -0.0000

Data Index: 962357 (The Pile)

Max Activating Token Index: 669