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

Dataset: The Pile

Neuron 3769 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: 0.6371. Min Range: -0.6371

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1842205 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1014140 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2923. Min Act: -0.0000

Data Index: 792248 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.3159. Min Act: -0.0000

Data Index: 758664 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2763. Min Act: -0.0000

Data Index: 253710 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1826545 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1512012 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1902364 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2310. Min Act: -0.0000

Data Index: 592616 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2237. Min Act: -0.0000

Data Index: 391530 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2023. Min Act: -0.0000

Data Index: 595023 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1986754 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2214. Min Act: -0.0000

Data Index: 904641 (The Pile)

Max Activating Token Index: 922

Text #13

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1400031 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1551315 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1797048 (The Pile)

Max Activating Token Index: 592

Text #16

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.1621. Min Act: -0.0000

Data Index: 953576 (The Pile)

Max Activating Token Index: 967

Text #17

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1385846 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1875097 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 0.6371. Min Range: -0.6371

Max Act: 0.2105. Min Act: -0.0000

Data Index: 538421 (The Pile)

Max Activating Token Index: 364