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

Dataset: The Pile

Neuron 3584 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3996. Min Act: -0.0000

Data Index: 305810 (The Pile)

Max Activating Token Index: 229

Text #1

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3582. Min Act: -0.0000

Data Index: 157585 (The Pile)

Max Activating Token Index: 19

Text #2

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1111782 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2985. Min Act: -0.0000

Data Index: 434541 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1200916 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2693. Min Act: -0.0000

Data Index: 725483 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1386497 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2713. Min Act: -0.0000

Data Index: 761080 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2564. Min Act: -0.0000

Data Index: 586493 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2624. Min Act: -0.0000

Data Index: 901967 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1431992 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2546. Min Act: -0.0000

Data Index: 470063 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2529. Min Act: -0.0000

Data Index: 52575 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2496. Min Act: -0.0000

Data Index: 866722 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2568. Min Act: -0.0000

Data Index: 724015 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3152. Min Act: -0.0000

Data Index: 254082 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1670767 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1844539 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1081194 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1643356 (The Pile)

Max Activating Token Index: 164