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

Dataset: The Pile

Neuron 95 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: 0.5121. Min Range: -0.5121

Max Act: 0.5121. Min Act: -0.0000

Data Index: 507487 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4428. Min Act: -0.0000

Data Index: 166704 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1911004 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4373. Min Act: -0.0000

Data Index: 828729 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4195. Min Act: -0.0000

Data Index: 197589 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1514474 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3960. Min Act: -0.0000

Data Index: 463614 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3680. Min Act: -0.0000

Data Index: 149219 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1849123 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3646. Min Act: -0.0000

Data Index: 946033 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1233210 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1018767 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3546. Min Act: -0.0000

Data Index: 382093 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3542. Min Act: -0.0000

Data Index: 770146 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3545. Min Act: -0.0000

Data Index: 290957 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3230. Min Act: -0.0000

Data Index: 893654 (The Pile)

Max Activating Token Index: 460

Text #16

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3627. Min Act: -0.0000

Data Index: 537626 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3399. Min Act: -0.0000

Data Index: 679855 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3277. Min Act: -0.0000

Data Index: 364451 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.5121. Min Range: -0.5121

Max Act: 0.3332. Min Act: -0.0000

Data Index: 206967 (The Pile)

Max Activating Token Index: 252