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

Dataset: The Pile

Neuron 3623 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4568. Min Range: -4.4568

Max Act: 4.0310. Min Act: -0.0000

Data Index: 1689339 (The Pile)

Max Activating Token Index: 668

Text #1

Max Range: 4.4568. Min Range: -4.4568

Max Act: 4.4568. Min Act: -0.0000

Data Index: 1401652 (The Pile)

Max Activating Token Index: 654

Text #2

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.8592. Min Act: -0.0000

Data Index: 1735915 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.9294. Min Act: -0.0000

Data Index: 1864484 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.5272. Min Act: -0.0000

Data Index: 949797 (The Pile)

Max Activating Token Index: 657

Text #5

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.7688. Min Act: -0.0000

Data Index: 400478 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.5118. Min Act: -0.0000

Data Index: 1279337 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.4453. Min Act: -0.0000

Data Index: 716438 (The Pile)

Max Activating Token Index: 930

Text #8

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.7565. Min Act: -0.0000

Data Index: 158142 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.3464. Min Act: -0.0000

Data Index: 229701 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.7048. Min Act: -0.0000

Data Index: 1254493 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.4349. Min Act: -0.0000

Data Index: 1713820 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.8411. Min Act: -0.0000

Data Index: 306768 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.7353. Min Act: -0.0000

Data Index: 319686 (The Pile)

Max Activating Token Index: 511

Text #14

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.5596. Min Act: -0.0000

Data Index: 1215284 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.3613. Min Act: -0.0000

Data Index: 315649 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.4148. Min Act: -0.0000

Data Index: 1760975 (The Pile)

Max Activating Token Index: 424

Text #17

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.6543. Min Act: -0.0000

Data Index: 1076809 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.7290. Min Act: -0.0000

Data Index: 701381 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 4.4568. Min Range: -4.4568

Max Act: 3.4758. Min Act: -0.0000

Data Index: 1582875 (The Pile)

Max Activating Token Index: 612