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

Dataset: The Pile

Neuron 2704 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: 0.3178. Min Range: -0.3178

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1924459 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2933. Min Act: -0.0000

Data Index: 44564 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1128541 (The Pile)

Max Activating Token Index: 826

Text #3

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2620. Min Act: -0.0000

Data Index: 616172 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2708. Min Act: -0.0000

Data Index: 418649 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2531. Min Act: -0.0000

Data Index: 141262 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1142037 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2608. Min Act: -0.0000

Data Index: 164848 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1746973 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1640450 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2705. Min Act: -0.0000

Data Index: 110179 (The Pile)

Max Activating Token Index: 614

Text #11

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1442763 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2733. Min Act: -0.0000

Data Index: 684779 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1160598 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2717. Min Act: -0.0000

Data Index: 601492 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2698. Min Act: -0.0000

Data Index: 459593 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2592. Min Act: -0.0000

Data Index: 880036 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2684. Min Act: -0.0000

Data Index: 969771 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1667036 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 0.3178. Min Range: -0.3178

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1334212 (The Pile)

Max Activating Token Index: 100