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

Dataset: The Pile

Neuron 2349 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: 0.4723. Min Range: -0.4723

Max Act: 0.4723. Min Act: -0.0000

Data Index: 761937 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3934. Min Act: -0.0000

Data Index: 489450 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1013122 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3764. Min Act: -0.0000

Data Index: 927178 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3644. Min Act: -0.0000

Data Index: 416952 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3691. Min Act: -0.0000

Data Index: 867993 (The Pile)

Max Activating Token Index: 589

Text #6

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3655. Min Act: -0.0000

Data Index: 561525 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3681. Min Act: -0.0000

Data Index: 178864 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3534. Min Act: -0.0000

Data Index: 300092 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3509. Min Act: -0.0000

Data Index: 708327 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1886616 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3647. Min Act: -0.0000

Data Index: 241423 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1320655 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3303. Min Act: -0.0000

Data Index: 829098 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1038976 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3713. Min Act: -0.0000

Data Index: 508008 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3346. Min Act: -0.0000

Data Index: 976873 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1668793 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3297. Min Act: -0.0000

Data Index: 249258 (The Pile)

Max Activating Token Index: 313

Text #19

Max Range: 0.4723. Min Range: -0.4723

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1335527 (The Pile)

Max Activating Token Index: 794