Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1272 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.6483. Min Act: -0.0000

Data Index: 95969 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.5218. Min Act: -0.0000

Data Index: 414294 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4746. Min Act: -0.0000

Data Index: 10426 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.5254. Min Act: -0.0000

Data Index: 53603 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4431. Min Act: -0.0000

Data Index: 40233 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3981. Min Act: -0.0000

Data Index: 403973 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1931347 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3823. Min Act: -0.0000

Data Index: 605109 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3983. Min Act: -0.0000

Data Index: 926413 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1622088 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1407616 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3635. Min Act: -0.0000

Data Index: 86512 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1910614 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1793875 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1265188 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.4686. Min Act: -0.0000

Data Index: 211458 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3083. Min Act: -0.0000

Data Index: 383313 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3812. Min Act: -0.0000

Data Index: 186914 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3468. Min Act: -0.0000

Data Index: 652538 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 0.6483. Min Range: -0.6483

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1240060 (The Pile)

Max Activating Token Index: 694