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

Dataset: The Pile

Neuron 659 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: 0.7923. Min Range: -0.7923

Max Act: 0.7693. Min Act: -0.0000

Data Index: 434584 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.7775. Min Act: -0.0000

Data Index: 37309 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.7923. Min Act: -0.0000

Data Index: 78807 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1605446 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.7538. Min Act: -0.0000

Data Index: 269330 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6766. Min Act: -0.0000

Data Index: 226108 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1235475 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6878. Min Act: -0.0000

Data Index: 560917 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1382902 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6443. Min Act: -0.0000

Data Index: 801430 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1833748 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1005434 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1071107 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1525019 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1566589 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.5696. Min Act: -0.0000

Data Index: 160571 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1965286 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1187793 (The Pile)

Max Activating Token Index: 368

Text #18

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.4943. Min Act: -0.0000

Data Index: 953023 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 0.7923. Min Range: -0.7923

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1308193 (The Pile)

Max Activating Token Index: 288