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

Dataset: The Pile

Neuron 1315 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1410046 (The Pile)

Max Activating Token Index: 699

Text #1

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.8242. Min Act: -0.0000

Data Index: 536088 (The Pile)

Max Activating Token Index: 378

Text #2

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7968. Min Act: -0.0000

Data Index: 847242 (The Pile)

Max Activating Token Index: 390

Text #3

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7686. Min Act: -0.0000

Data Index: 148491 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7647. Min Act: -0.0000

Data Index: 46797 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1393909 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1740610 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7068. Min Act: -0.0000

Data Index: 529725 (The Pile)

Max Activating Token Index: 318

Text #8

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7744. Min Act: -0.0000

Data Index: 97516 (The Pile)

Max Activating Token Index: 476

Text #9

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1753132 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6704. Min Act: -0.0000

Data Index: 829408 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1447247 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1218967 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6490. Min Act: -0.0000

Data Index: 38148 (The Pile)

Max Activating Token Index: 430

Text #14

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.7032. Min Act: -0.0000

Data Index: 531821 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6049. Min Act: -0.0000

Data Index: 205830 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1108496 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1651632 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.5934. Min Act: -0.0000

Data Index: 61717 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 0.8381. Min Range: -0.8381

Max Act: 0.5918. Min Act: -0.0000

Data Index: 650531 (The Pile)

Max Activating Token Index: 716