Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3791 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.5579. Min Act: -0.0000

Data Index: 106836 (The Pile)

Max Activating Token Index: 606

Text #1

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.4301. Min Act: -0.0000

Data Index: 562103 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1277088 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.2444. Min Act: 0.0000

Data Index: 1441023 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1292703 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1359. Min Act: -0.0000

Data Index: 441013 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.1544. Min Act: -0.0000

Data Index: 119031 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.9790. Min Act: -0.0000

Data Index: 697100 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1690289 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1678686 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1828729 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.9918. Min Act: -0.0000

Data Index: 878146 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1006181 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 1.5579. Min Range: -1.5579

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1680997 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1625027 (The Pile)

Max Activating Token Index: 689

Text #15

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.9400. Min Act: -0.0000

Data Index: 523600 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1730139 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.8769. Min Act: -0.0000

Data Index: 327132 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1757390 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 1.5579. Min Range: -1.5579

Max Act: 0.8560. Min Act: -0.0000

Data Index: 426313 (The Pile)

Max Activating Token Index: 679