Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3589 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.4430. Min Act: -0.0000

Data Index: 1635320 (The Pile)

Max Activating Token Index: 986

Text #1

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.6362. Min Act: -0.0000

Data Index: 920915 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3824. Min Act: -0.0000

Data Index: 656055 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1132954 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1599115 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1519482 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3364. Min Act: -0.0000

Data Index: 49524 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3682. Min Act: -0.0000

Data Index: 673951 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1118326 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.3177. Min Act: -0.0000

Data Index: 699026 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.2383. Min Act: -0.0000

Data Index: 1135176 (The Pile)

Max Activating Token Index: 695

Text #11

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.1696. Min Act: -0.0000

Data Index: 270062 (The Pile)

Max Activating Token Index: 791

Text #12

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.2308. Min Act: -0.0000

Data Index: 722419 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.0011. Min Act: -0.0000

Data Index: 106271 (The Pile)

Max Activating Token Index: 536

Text #14

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1468000 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.2434. Min Act: -0.0000

Data Index: 331625 (The Pile)

Max Activating Token Index: 282

Text #16

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.1749. Min Act: -0.0000

Data Index: 194181 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1691729 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.1634. Min Act: -0.0000

Data Index: 481065 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 1.6362. Min Range: -1.6362

Max Act: 1.1994. Min Act: -0.0000

Data Index: 160972 (The Pile)

Max Activating Token Index: 553