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

Dataset: The Pile

Neuron 3213 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: 0.9005. Min Range: -0.9005

Max Act: 0.9005. Min Act: -0.0000

Data Index: 60914 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.8394. Min Act: -0.0000

Data Index: 58793 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.7228. Min Act: -0.0000

Data Index: 971274 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1516109 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1772644 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6738. Min Act: -0.0000

Data Index: 193920 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1279383 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6770. Min Act: -0.0000

Data Index: 71464 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1041413 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6229. Min Act: -0.0000

Data Index: 630136 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6134. Min Act: -0.0000

Data Index: 224192 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.5982. Min Act: -0.0000

Data Index: 890282 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1043509 (The Pile)

Max Activating Token Index: 12

Text #13

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.5832. Min Act: -0.0001

Data Index: 1308868 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1250486 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1364710 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6002. Min Act: -0.0000

Data Index: 806372 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.6057. Min Act: -0.0000

Data Index: 181652 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1661926 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 0.9005. Min Range: -0.9005

Max Act: 0.5537. Min Act: -0.0000

Data Index: 251502 (The Pile)

Max Activating Token Index: 606