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

Dataset: The Pile

Neuron 3781 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: 0.4602. Min Range: -0.4602

Max Act: 0.4602. Min Act: -0.0000

Data Index: 337297 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1348342 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1426332 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1671526 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3389. Min Act: -0.0000

Data Index: 245610 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3622. Min Act: -0.0000

Data Index: 661055 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3490. Min Act: -0.0000

Data Index: 717873 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3616. Min Act: -0.0000

Data Index: 614084 (The Pile)

Max Activating Token Index: 30

Text #8

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1793537 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3695. Min Act: -0.0000

Data Index: 794545 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3383. Min Act: -0.0000

Data Index: 353784 (The Pile)

Max Activating Token Index: 708

Text #11

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3363. Min Act: -0.0000

Data Index: 275726 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3367. Min Act: -0.0000

Data Index: 275947 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1968800 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1285669 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3447. Min Act: -0.0000

Data Index: 726322 (The Pile)

Max Activating Token Index: 305

Text #16

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1636228 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1179142 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1648656 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.4602. Min Range: -0.4602

Max Act: 0.3277. Min Act: -0.0000

Data Index: 415849 (The Pile)

Max Activating Token Index: 472