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

Dataset: The Pile

Neuron 2935 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1764837 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2768. Min Act: -0.0000

Data Index: 169387 (The Pile)

Max Activating Token Index: 689

Text #2

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1068595 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2961. Min Act: -0.0000

Data Index: 251106 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2862. Min Act: -0.0000

Data Index: 90592 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1102701 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1425773 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1763342 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2738. Min Act: -0.0000

Data Index: 681664 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1475780 (The Pile)

Max Activating Token Index: 133

Text #10

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1213594 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1119813 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2416. Min Act: -0.0000

Data Index: 339357 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1449565 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1707995 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2485. Min Act: -0.0000

Data Index: 665146 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1099667 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1552520 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2500. Min Act: -0.0000

Data Index: 700311 (The Pile)

Max Activating Token Index: 859

Text #19

Max Range: 0.3098. Min Range: -0.3098

Max Act: 0.2436. Min Act: -0.0000

Data Index: 705216 (The Pile)

Max Activating Token Index: 291