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

Dataset: The Pile

Neuron 297 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0720. Min Range: -1.0720

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1778212 (The Pile)

Max Activating Token Index: 99

Text #1

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.9607. Min Act: -0.0000

Data Index: 2535 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8567. Min Act: -0.0000

Data Index: 925266 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8797. Min Act: -0.0000

Data Index: 518230 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1411966 (The Pile)

Max Activating Token Index: 388

Text #5

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8545. Min Act: -0.0000

Data Index: 1095799 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1406132 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8279. Min Act: -0.0000

Data Index: 390019 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7899. Min Act: -0.0000

Data Index: 254371 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1986790 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1774662 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1425289 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1568539 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7636. Min Act: -0.0000

Data Index: 11447 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1109309 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1937606 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1744658 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1935685 (The Pile)

Max Activating Token Index: 406

Text #18

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1015229 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 1.0720. Min Range: -1.0720

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1398479 (The Pile)

Max Activating Token Index: 442