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

Dataset: The Pile

Neuron 1802 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.4514. Min Act: -0.0000

Data Index: 1699600 (The Pile)

Max Activating Token Index: 679

Text #1

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.2132. Min Act: -0.0000

Data Index: 870168 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1560085 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.3558. Min Act: -0.0000

Data Index: 368642 (The Pile)

Max Activating Token Index: 375

Text #4

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1437690 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1213449 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1652368 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1482348 (The Pile)

Max Activating Token Index: 202

Text #8

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1917. Min Act: -0.0000

Data Index: 211845 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.2543. Min Act: -0.0000

Data Index: 499811 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1498. Min Act: -0.0000

Data Index: 652765 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.1303. Min Act: -0.0000

Data Index: 1195389 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1797359 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1776186 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 1.4514. Min Range: -1.4514

Max Act: 1.0047. Min Act: -0.0000

Data Index: 669879 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9667. Min Act: -0.0000

Data Index: 478426 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1977034 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.8857. Min Act: -0.0000

Data Index: 793069 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.9100. Min Act: -0.0000

Data Index: 399753 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 1.4514. Min Range: -1.4514

Max Act: 0.8862. Min Act: -0.0000

Data Index: 504979 (The Pile)

Max Activating Token Index: 436