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

Dataset: The Pile

Neuron 2822 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: 0.3069. Min Range: -0.3069

Max Act: 0.2644. Min Act: -0.0000

Data Index: 221679 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.3069. Min Act: -0.0000

Data Index: 254164 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1187687 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1988774 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2838. Min Act: -0.0000

Data Index: 450647 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1760954 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1366629 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1793773 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1856083 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2501. Min Act: -0.0001

Data Index: 752583 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2629. Min Act: -0.0000

Data Index: 701385 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1417649 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1204335 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1394281 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1867803 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1479956 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1780198 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2149. Min Act: -0.0000

Data Index: 641028 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1745635 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 0.3069. Min Range: -0.3069

Max Act: 0.2408. Min Act: -0.0000

Data Index: 286781 (The Pile)

Max Activating Token Index: 359