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

Dataset: The Pile

Neuron 3188 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: 0.7628. Min Range: -0.7628

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1436455 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5882. Min Act: -0.0000

Data Index: 259342 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5378. Min Act: -0.0000

Data Index: 547250 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1188632 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4925. Min Act: -0.0000

Data Index: 204936 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5397. Min Act: -0.0000

Data Index: 268911 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1104147 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1557051 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1363768 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1570275 (The Pile)

Max Activating Token Index: 375

Text #10

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1176968 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4402. Min Act: -0.0000

Data Index: 693271 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1432012 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1030883 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1091254 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4346. Min Act: -0.0000

Data Index: 963406 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4363. Min Act: -0.0000

Data Index: 240206 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1766271 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4565. Min Act: -0.0000

Data Index: 561703 (The Pile)

Max Activating Token Index: 735

Text #19

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4291. Min Act: -0.0000

Data Index: 194618 (The Pile)

Max Activating Token Index: 64