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

Dataset: The Pile

Neuron 541 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: 1.7651. Min Range: -1.7651

Max Act: 1.7651. Min Act: -0.0000

Data Index: 23962 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.6346. Min Act: -0.0000

Data Index: 820598 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1639162 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.6178. Min Act: -0.0000

Data Index: 975502 (The Pile)

Max Activating Token Index: 534

Text #4

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.4853. Min Act: -0.0000

Data Index: 811825 (The Pile)

Max Activating Token Index: 110

Text #5

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1461337 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1979349 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.4096. Min Act: -0.0000

Data Index: 660623 (The Pile)

Max Activating Token Index: 725

Text #8

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3255. Min Act: -0.0000

Data Index: 1483699 (The Pile)

Max Activating Token Index: 620

Text #9

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2994. Min Act: -0.0000

Data Index: 1179441 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1170217 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3724. Min Act: -0.0000

Data Index: 906338 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3680. Min Act: -0.0000

Data Index: 437893 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2276. Min Act: -0.0000

Data Index: 114445 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3145. Min Act: -0.0000

Data Index: 911021 (The Pile)

Max Activating Token Index: 905

Text #15

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1590428 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.3992. Min Act: -0.0000

Data Index: 1627488 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1816871 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1564. Min Act: -0.0000

Data Index: 1418612 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 1.7651. Min Range: -1.7651

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1030099 (The Pile)

Max Activating Token Index: 323