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

Dataset: The Pile

Neuron 2626 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: 3.1720. Min Range: -3.1720

Max Act: 3.1720. Min Act: -0.0000

Data Index: 1799746 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.5558. Min Act: -0.0000

Data Index: 129095 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.6108. Min Act: -0.0000

Data Index: 676208 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.8623. Min Act: -0.0000

Data Index: 9895 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.0428. Min Act: -0.0000

Data Index: 1856369 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1884170 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.7967. Min Act: -0.0000

Data Index: 1489440 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.5908. Min Act: -0.0000

Data Index: 540229 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.7463. Min Act: -0.0000

Data Index: 1298346 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.7223. Min Act: 0.0000

Data Index: 1205105 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.7070. Min Act: -0.0000

Data Index: 1051073 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.8812. Min Act: -0.0000

Data Index: 617860 (The Pile)

Max Activating Token Index: 168

Text #12

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.8154. Min Act: -0.0000

Data Index: 1189607 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.5064. Min Act: -0.0000

Data Index: 386658 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.4965. Min Act: -0.0000

Data Index: 1421494 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.5556. Min Act: 0.0000

Data Index: 1809403 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1355431 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.5713. Min Act: -0.0000

Data Index: 490958 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.5778. Min Act: -0.0000

Data Index: 1691992 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 3.1720. Min Range: -3.1720

Max Act: 1.6280. Min Act: -0.0000

Data Index: 1628135 (The Pile)

Max Activating Token Index: 888