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

Dataset: The Pile

Neuron 2686 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1845297 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1822408 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3442. Min Act: -0.0000

Data Index: 787334 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2964. Min Act: -0.0000

Data Index: 138194 (The Pile)

Max Activating Token Index: 575

Text #4

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1632004 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1260892 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2664. Min Act: -0.0000

Data Index: 606557 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2678. Min Act: 0.0000

Data Index: 1373894 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2577. Min Act: -0.0000

Data Index: 878670 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1638542 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.3050. Min Act: -0.0000

Data Index: 802663 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2821. Min Act: -0.0000

Data Index: 896124 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2697. Min Act: -0.0000

Data Index: 592015 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1404009 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2737. Min Act: -0.0000

Data Index: 567619 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2670. Min Act: -0.0000

Data Index: 444681 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2565. Min Act: -0.0000

Data Index: 120423 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1004195 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2630. Min Act: -0.0000

Data Index: 644222 (The Pile)

Max Activating Token Index: 510

Text #19

Max Range: 0.4684. Min Range: -0.4684

Max Act: 0.2786. Min Act: -0.0000

Data Index: 205313 (The Pile)

Max Activating Token Index: 169