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

Dataset: The Pile

Neuron 3749 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: 1.9315. Min Range: -1.9315

Max Act: 1.9315. Min Act: -0.0000

Data Index: 632667 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8358. Min Act: -0.0000

Data Index: 200486 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8314. Min Act: -0.0000

Data Index: 107608 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8743. Min Act: -0.0000

Data Index: 889477 (The Pile)

Max Activating Token Index: 862

Text #4

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7723. Min Act: -0.0000

Data Index: 983385 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8616. Min Act: -0.0000

Data Index: 759938 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7959. Min Act: -0.0000

Data Index: 1498023 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1201169 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7830. Min Act: -0.0000

Data Index: 981710 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7917. Min Act: -0.0000

Data Index: 1602387 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8272. Min Act: -0.0000

Data Index: 1471794 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.6627. Min Act: -0.0000

Data Index: 1697420 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1351205 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8419. Min Act: -0.0000

Data Index: 318251 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.6599. Min Act: -0.0000

Data Index: 1497533 (The Pile)

Max Activating Token Index: 392

Text #15

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.8048. Min Act: -0.0000

Data Index: 439999 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7434. Min Act: -0.0000

Data Index: 1788763 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7878. Min Act: -0.0000

Data Index: 446237 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1551081 (The Pile)

Max Activating Token Index: 193

Text #19

Max Range: 1.9315. Min Range: -1.9315

Max Act: 1.7359. Min Act: -0.0000

Data Index: 878913 (The Pile)

Max Activating Token Index: 21