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

Dataset: The Pile

Neuron 3755 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1807594 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7010. Min Act: -0.0000

Data Index: 218093 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6011. Min Act: -0.0000

Data Index: 501436 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1432621 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1736030 (The Pile)

Max Activating Token Index: 1022

Text #5

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1776043 (The Pile)

Max Activating Token Index: 533

Text #6

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5688. Min Act: -0.0000

Data Index: 998269 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5891. Min Act: -0.0000

Data Index: 485378 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1940579 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5503. Min Act: -0.0000

Data Index: 638157 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1813066 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1113680 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1453762 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1414667 (The Pile)

Max Activating Token Index: 251

Text #14

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1402324 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1068610 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4928. Min Act: 0.0000

Data Index: 243320 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1203172 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1956987 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.4364. Min Act: -0.0000

Data Index: 621045 (The Pile)

Max Activating Token Index: 132