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

Dataset: The Pile

Neuron 2192 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.3576. Min Act: -0.0000

Data Index: 50239 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1859620 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1964129 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.1611. Min Act: -0.0000

Data Index: 152807 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.1586. Min Act: -0.0000

Data Index: 514133 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1177150 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.1645. Min Act: -0.0000

Data Index: 41965 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.0819. Min Act: -0.0000

Data Index: 1749359 (The Pile)

Max Activating Token Index: 604

Text #8

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.0196. Min Act: -0.0000

Data Index: 664545 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.0538. Min Act: -0.0000

Data Index: 1891530 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.0086. Min Act: -0.0000

Data Index: 746411 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 1.4328. Min Range: -1.4328

Max Act: 0.9810. Min Act: -0.0000

Data Index: 466103 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 1.4328. Min Range: -1.4328

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1667426 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.4328. Min Range: -1.4328

Max Act: 0.9439. Min Act: -0.0000

Data Index: 769317 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1189738 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 1.4328. Min Range: -1.4328

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1091065 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.0400. Min Act: -0.0000

Data Index: 996072 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 1.4328. Min Range: -1.4328

Max Act: 0.9446. Min Act: -0.0000

Data Index: 399295 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.4328. Min Range: -1.4328

Max Act: 1.0042. Min Act: -0.0000

Data Index: 64383 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 1.4328. Min Range: -1.4328

Max Act: 0.9826. Min Act: -0.0000

Data Index: 256809 (The Pile)

Max Activating Token Index: 152