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

Dataset: The Pile

Neuron 130 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1739643 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1065006 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.7553. Min Act: -0.0000

Data Index: 1010271 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5241. Min Act: -0.0000

Data Index: 1032145 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5456. Min Act: -0.0000

Data Index: 1553833 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1480062 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5035. Min Act: -0.0000

Data Index: 766211 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4350. Min Act: -0.0000

Data Index: 145429 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3392. Min Act: -0.0000

Data Index: 877260 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4264. Min Act: -0.0000

Data Index: 80027 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3455. Min Act: -0.0000

Data Index: 112965 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3104. Min Act: -0.0000

Data Index: 668450 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1010558 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.2382. Min Act: -0.0000

Data Index: 730654 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3667. Min Act: -0.0000

Data Index: 453551 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.2685. Min Act: -0.0000

Data Index: 860922 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3891. Min Act: -0.0000

Data Index: 680081 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.2620. Min Act: -0.0000

Data Index: 111512 (The Pile)

Max Activating Token Index: 927

Text #18

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1094333 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.2707. Min Act: -0.0000

Data Index: 511467 (The Pile)

Max Activating Token Index: 495