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

Dataset: The Pile

Neuron 2404 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: 0.7515. Min Range: -0.7515

Max Act: 0.6826. Min Act: -0.0000

Data Index: 747367 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7515. Min Act: -0.0000

Data Index: 757296 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1976508 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1364815 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1919326 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.7372. Min Act: -0.0000

Data Index: 650744 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6550. Min Act: -0.0000

Data Index: 770865 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1827896 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6424. Min Act: -0.0000

Data Index: 232161 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1756178 (The Pile)

Max Activating Token Index: 416

Text #10

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1103496 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6199. Min Act: -0.0000

Data Index: 464619 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6794. Min Act: -0.0000

Data Index: 387636 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.5983. Min Act: -0.0000

Data Index: 751497 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6493. Min Act: -0.0000

Data Index: 971352 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6437. Min Act: -0.0000

Data Index: 287781 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6682. Min Act: -0.0000

Data Index: 755419 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1679023 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6173. Min Act: -0.0000

Data Index: 403302 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.7515. Min Range: -0.7515

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1419562 (The Pile)

Max Activating Token Index: 409