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

Dataset: The Pile

Neuron 2556 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: 1.8556. Min Range: -1.8556

Max Act: 1.8556. Min Act: -0.0000

Data Index: 1783866 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.5231. Min Act: -0.0000

Data Index: 331294 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.4116. Min Act: -0.0000

Data Index: 573188 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.4925. Min Act: -0.0001

Data Index: 196402 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3801. Min Act: -0.0000

Data Index: 1021346 (The Pile)

Max Activating Token Index: 478

Text #5

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.2678. Min Act: -0.0000

Data Index: 772218 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.2553. Min Act: -0.0000

Data Index: 209054 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3714. Min Act: -0.0000

Data Index: 1423909 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1928198 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3153. Min Act: -0.0000

Data Index: 261774 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3579. Min Act: -0.0000

Data Index: 595439 (The Pile)

Max Activating Token Index: 302

Text #11

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.4117. Min Act: -0.0000

Data Index: 908341 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3244. Min Act: -0.0000

Data Index: 488516 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3084. Min Act: -0.0000

Data Index: 758828 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3780. Min Act: -0.0000

Data Index: 642102 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3405. Min Act: -0.0000

Data Index: 1084228 (The Pile)

Max Activating Token Index: 66

Text #16

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1031556 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3273. Min Act: -0.0000

Data Index: 934229 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.2911. Min Act: -0.0000

Data Index: 505802 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 1.8556. Min Range: -1.8556

Max Act: 1.3649. Min Act: -0.0000

Data Index: 394224 (The Pile)

Max Activating Token Index: 86