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

Dataset: The Pile

Neuron 1651 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6839. Min Act: -0.0000

Data Index: 577573 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6003. Min Act: -0.0000

Data Index: 894119 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.7323. Min Act: -0.0000

Data Index: 1647252 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2223. Min Act: 0.0001

Data Index: 226875 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1597432 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2283. Min Act: -0.0000

Data Index: 709925 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2246. Min Act: -0.0000

Data Index: 375419 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1178238 (The Pile)

Max Activating Token Index: 936

Text #8

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0967. Min Act: 0.0000

Data Index: 380112 (The Pile)

Max Activating Token Index: 756

Text #9

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0649. Min Act: -0.0000

Data Index: 781553 (The Pile)

Max Activating Token Index: 443

Text #10

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1123387 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0294. Min Act: -0.0000

Data Index: 488454 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0644. Min Act: -0.0000

Data Index: 775588 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0172. Min Act: -0.0000

Data Index: 1603661 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.7323. Min Range: -1.7323

Max Act: 0.9483. Min Act: -0.0000

Data Index: 674924 (The Pile)

Max Activating Token Index: 951

Text #15

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1865291 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 1.7323. Min Range: -1.7323

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1973102 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 1.7323. Min Range: -1.7323

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1664664 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 1.7323. Min Range: -1.7323

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1059418 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 1.7323. Min Range: -1.7323

Max Act: 0.9938. Min Act: -0.0000

Data Index: 862761 (The Pile)

Max Activating Token Index: 409