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

Dataset: The Pile

Neuron 3919 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: 0.5651. Min Range: -0.5651

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1395378 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1796011 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1367840 (The Pile)

Max Activating Token Index: 994

Text #3

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4700. Min Act: -0.0000

Data Index: 845315 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4566. Min Act: -0.0000

Data Index: 107552 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4602. Min Act: -0.0000

Data Index: 620705 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1042165 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1273932 (The Pile)

Max Activating Token Index: 855

Text #8

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1815538 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1231509 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.4066. Min Act: -0.0000

Data Index: 354796 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3987. Min Act: -0.0000

Data Index: 572451 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1762744 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3946. Min Act: -0.0000

Data Index: 572491 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1241882 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1452451 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3878. Min Act: -0.0000

Data Index: 381343 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1172539 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3636. Min Act: -0.0000

Data Index: 36343 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 0.5651. Min Range: -0.5651

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1666785 (The Pile)

Max Activating Token Index: 208