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

Dataset: The Pile

Neuron 2082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1765818 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2753. Min Act: -0.0000

Data Index: 38959 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2690. Min Act: -0.0000

Data Index: 587672 (The Pile)

Max Activating Token Index: 48

Text #3

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2669. Min Act: -0.0000

Data Index: 7852 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1968916 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2711. Min Act: -0.0000

Data Index: 477366 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2351. Min Act: -0.0000

Data Index: 1426064 (The Pile)

Max Activating Token Index: 696

Text #7

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1159067 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1954153 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2395. Min Act: -0.0000

Data Index: 325946 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2383. Min Act: -0.0000

Data Index: 1293306 (The Pile)

Max Activating Token Index: 69

Text #11

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1890659 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2359. Min Act: -0.0000

Data Index: 182387 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2382. Min Act: -0.0000

Data Index: 809449 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2307. Min Act: -0.0000

Data Index: 781409 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2149. Min Act: -0.0000

Data Index: 611620 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1800473 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2443. Min Act: -0.0000

Data Index: 675358 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1514571 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.3041. Min Range: -0.3041

Max Act: 0.2156. Min Act: -0.0000

Data Index: 505446 (The Pile)

Max Activating Token Index: 998