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

Dataset: The Pile

Neuron 2016 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1334420 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3596. Min Act: -0.0000

Data Index: 490967 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1470785 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1050438 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3490. Min Act: -0.0000

Data Index: 554906 (The Pile)

Max Activating Token Index: 649

Text #5

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3390. Min Act: -0.0000

Data Index: 248643 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3594. Min Act: -0.0000

Data Index: 1409387 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1265520 (The Pile)

Max Activating Token Index: 636

Text #8

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3362. Min Act: -0.0000

Data Index: 457950 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3299. Min Act: -0.0000

Data Index: 253094 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3668. Min Act: -0.0000

Data Index: 77111 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3191. Min Act: -0.0000

Data Index: 916557 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3521. Min Act: -0.0000

Data Index: 442482 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1364242 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1644999 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1636768 (The Pile)

Max Activating Token Index: 796

Text #16

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1669396 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1780372 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1578187 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 0.3982. Min Range: -0.3982

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1614276 (The Pile)

Max Activating Token Index: 426