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

Dataset: The Pile

Neuron 3087 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: 0.6975. Min Range: -0.6975

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1769485 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1082078 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1763584 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6048. Min Act: -0.0000

Data Index: 121520 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1447775 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1635431 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5365. Min Act: -0.0000

Data Index: 407559 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1483473 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1510107 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5808. Min Act: 0.0000

Data Index: 477431 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1693406 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5670. Min Act: -0.0000

Data Index: 233733 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1159974 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5421. Min Act: -0.0000

Data Index: 561024 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1612571 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5334. Min Act: -0.0000

Data Index: 292983 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1723772 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5429. Min Act: -0.0000

Data Index: 829471 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5114. Min Act: -0.0000

Data Index: 839366 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 0.6975. Min Range: -0.6975

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1341212 (The Pile)

Max Activating Token Index: 588