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

Dataset: The Pile

Neuron 4417 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3383. Min Act: -0.0000

Data Index: 40923 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3515. Min Act: -0.0000

Data Index: 450096 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3523. Min Act: -0.0000

Data Index: 13797 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1551929 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1466107 (The Pile)

Max Activating Token Index: 816

Text #5

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3064. Min Act: -0.0000

Data Index: 475551 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3155. Min Act: -0.0000

Data Index: 298858 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2854. Min Act: -0.0000

Data Index: 316058 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1012108 (The Pile)

Max Activating Token Index: 712

Text #9

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3195. Min Act: -0.0000

Data Index: 960391 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1755661 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1293308 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3080. Min Act: -0.0000

Data Index: 61122 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1540813 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1235670 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1154899 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1612833 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1763411 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1452633 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2649. Min Act: -0.0000

Data Index: 952466 (The Pile)

Max Activating Token Index: 62