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

Dataset: The Pile

Neuron 3831 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.6772. Min Act: -0.0000

Data Index: 527402 (The Pile)

Max Activating Token Index: 759

Text #1

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1125526 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1558048 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3351. Min Act: -0.0000

Data Index: 64887 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3366. Min Act: -0.0000

Data Index: 121393 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3250. Min Act: -0.0000

Data Index: 664768 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3279. Min Act: -0.0000

Data Index: 305031 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1167043 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1126566 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3381. Min Act: -0.0000

Data Index: 252317 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3551. Min Act: -0.0000

Data Index: 371221 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1895239 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.2938. Min Act: -0.0000

Data Index: 569527 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3248. Min Act: -0.0000

Data Index: 69528 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3117. Min Act: -0.0000

Data Index: 54319 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3302. Min Act: -0.0000

Data Index: 417583 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3301. Min Act: -0.0000

Data Index: 975128 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1709823 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3170. Min Act: -0.0000

Data Index: 177431 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.6772. Min Range: -0.6772

Max Act: 0.3467. Min Act: -0.0000

Data Index: 287587 (The Pile)

Max Activating Token Index: 972