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

Dataset: The Pile

Neuron 2771 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1364549 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.7302. Min Act: -0.0000

Data Index: 540723 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.6691. Min Act: -0.0000

Data Index: 875918 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.7070. Min Act: 0.0000

Data Index: 505342 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.7204. Min Act: -0.0000

Data Index: 74593 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.6512. Min Act: -0.0000

Data Index: 478358 (The Pile)

Max Activating Token Index: 129

Text #6

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1733526 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5804. Min Act: -0.0000

Data Index: 453260 (The Pile)

Max Activating Token Index: 547

Text #8

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5812. Min Act: 0.0000

Data Index: 365568 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5459. Min Act: 0.0000

Data Index: 1650452 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1502649 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1017191 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1597070 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4785. Min Act: -0.0000

Data Index: 747739 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.5022. Min Act: -0.0000

Data Index: 90121 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1525193 (The Pile)

Max Activating Token Index: 834

Text #16

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1518506 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1340123 (The Pile)

Max Activating Token Index: 787

Text #18

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1644275 (The Pile)

Max Activating Token Index: 309

Text #19

Max Range: 0.7359. Min Range: -0.7359

Max Act: 0.4283. Min Act: -0.0000

Data Index: 142799 (The Pile)

Max Activating Token Index: 311