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

Dataset: The Pile

Neuron 4758 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: 0.4462. Min Range: -0.4462

Max Act: 0.4363. Min Act: -0.0000

Data Index: 302636 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.4462. Min Act: -0.0000

Data Index: 20659 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1166773 (The Pile)

Max Activating Token Index: 561

Text #3

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3928. Min Act: -0.0000

Data Index: 98178 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3965. Min Act: -0.0000

Data Index: 322632 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1172009 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1463599 (The Pile)

Max Activating Token Index: 68

Text #7

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3580. Min Act: -0.0000

Data Index: 81389 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1958396 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1234948 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1865597 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3563. Min Act: -0.0000

Data Index: 711083 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3534. Min Act: -0.0000

Data Index: 653636 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1494389 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3640. Min Act: -0.0000

Data Index: 937427 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1221636 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1006015 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1995045 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3340. Min Act: -0.0000

Data Index: 114093 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.4462. Min Range: -0.4462

Max Act: 0.3188. Min Act: -0.0000

Data Index: 290240 (The Pile)

Max Activating Token Index: 667