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

Dataset: The Pile

Neuron 3580 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.3467. Min Act: -0.0000

Data Index: 380346 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.3011. Min Act: -0.0000

Data Index: 837833 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1723603 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2555. Min Act: -0.0000

Data Index: 516251 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2619. Min Act: -0.0000

Data Index: 189614 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1399346 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1347376 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1589055 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2612. Min Act: -0.0000

Data Index: 330577 (The Pile)

Max Activating Token Index: 462

Text #9

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1708505 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2663. Min Act: -0.0000

Data Index: 227732 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1206359 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2384. Min Act: -0.0000

Data Index: 503438 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1486708 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1474230 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1055960 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2267. Min Act: -0.0000

Data Index: 644646 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1559117 (The Pile)

Max Activating Token Index: 688

Text #18

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2059. Min Act: -0.0000

Data Index: 653543 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.3467. Min Range: -0.3467

Max Act: 0.2207. Min Act: -0.0000

Data Index: 39524 (The Pile)

Max Activating Token Index: 275