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

Dataset: The Pile

Neuron 4852 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.9788. Min Act: -0.0000

Data Index: 1178409 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.3345. Min Act: -0.0000

Data Index: 388642 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.5541. Min Act: -0.0000

Data Index: 1210364 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.2534. Min Act: -0.0000

Data Index: 1109980 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.1749. Min Act: -0.0000

Data Index: 940048 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.9159. Min Act: -0.0000

Data Index: 1926749 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.1458. Min Act: -0.0000

Data Index: 1752696 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.0597. Min Act: -0.0000

Data Index: 1910113 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.9786. Min Act: -0.0000

Data Index: 1221593 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.9312. Min Act: -0.0000

Data Index: 944056 (The Pile)

Max Activating Token Index: 442

Text #10

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.0641. Min Act: -0.0000

Data Index: 749803 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 3.9788. Min Range: -3.9788

Max Act: 3.0097. Min Act: -0.0000

Data Index: 1320099 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.6179. Min Act: -0.0000

Data Index: 1616684 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.8579. Min Act: -0.0000

Data Index: 1832546 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.5752. Min Act: -0.0000

Data Index: 1901668 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.5584. Min Act: -0.0000

Data Index: 722649 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.5609. Min Act: -0.0000

Data Index: 593531 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.6554. Min Act: -0.0000

Data Index: 925905 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.3856. Min Act: -0.0000

Data Index: 1218915 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 3.9788. Min Range: -3.9788

Max Act: 2.5117. Min Act: -0.0000

Data Index: 507040 (The Pile)

Max Activating Token Index: 274