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

Dataset: The Pile

Neuron 2984 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: 1.6329. Min Range: -1.6329

Max Act: 1.6329. Min Act: -0.0000

Data Index: 1783082 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1028369 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.5441. Min Act: -0.0000

Data Index: 342793 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1657646 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.4706. Min Act: -0.0000

Data Index: 367802 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1283534 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1231854 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.4843. Min Act: -0.0000

Data Index: 1221773 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.4133. Min Act: -0.0000

Data Index: 1918303 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1393817 (The Pile)

Max Activating Token Index: 991

Text #10

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1737870 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3328. Min Act: -0.0000

Data Index: 57452 (The Pile)

Max Activating Token Index: 898

Text #12

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1442984 (The Pile)

Max Activating Token Index: 562

Text #13

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1083344 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.3512. Min Act: -0.0000

Data Index: 126723 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1989458 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2523. Min Act: -0.0000

Data Index: 265320 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1270117 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.2968. Min Act: -0.0000

Data Index: 770468 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 1.6329. Min Range: -1.6329

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1916420 (The Pile)

Max Activating Token Index: 139