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

Dataset: The Pile

Neuron 2273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.9411. Min Act: -0.0000

Data Index: 1931009 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.6512. Min Act: -0.0000

Data Index: 954343 (The Pile)

Max Activating Token Index: 731

Text #2

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.7563. Min Act: -0.0000

Data Index: 679861 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.2457. Min Act: -0.0000

Data Index: 1891225 (The Pile)

Max Activating Token Index: 677

Text #4

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.4267. Min Act: -0.0000

Data Index: 1050098 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.3984. Min Act: -0.0000

Data Index: 1416660 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.3474. Min Act: -0.0000

Data Index: 1207789 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0418. Min Act: -0.0000

Data Index: 795410 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.2893. Min Act: -0.0000

Data Index: 726796 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1069. Min Act: -0.0000

Data Index: 1056570 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0431. Min Act: -0.0000

Data Index: 364102 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1784. Min Act: -0.0000

Data Index: 299045 (The Pile)

Max Activating Token Index: 707

Text #12

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0546. Min Act: -0.0000

Data Index: 1458528 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1383. Min Act: -0.0000

Data Index: 1135097 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 3.9411. Min Range: -3.9411

Max Act: 2.9948. Min Act: -0.0000

Data Index: 1406097 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.1150. Min Act: -0.0000

Data Index: 1486963 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0859. Min Act: -0.0000

Data Index: 344252 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 3.9411. Min Range: -3.9411

Max Act: 2.9442. Min Act: -0.0000

Data Index: 542069 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0651. Min Act: -0.0000

Data Index: 999072 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 3.9411. Min Range: -3.9411

Max Act: 3.0592. Min Act: -0.0000

Data Index: 796223 (The Pile)

Max Activating Token Index: 262