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

Dataset: The Pile

Neuron 1924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.7087. Min Act: -0.0000

Data Index: 411631 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5865. Min Act: -0.0000

Data Index: 533780 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5119. Min Act: -0.0000

Data Index: 315312 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5187. Min Act: 0.0000

Data Index: 67569 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4908. Min Act: -0.0000

Data Index: 479114 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1840432 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.5080. Min Act: -0.0000

Data Index: 566894 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1192383 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4716. Min Act: -0.0000

Data Index: 914390 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1809507 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4656. Min Act: -0.0000

Data Index: 517709 (The Pile)

Max Activating Token Index: 162

Text #11

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1047153 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1756357 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4496. Min Act: -0.0000

Data Index: 452701 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4447. Min Act: -0.0000

Data Index: 510885 (The Pile)

Max Activating Token Index: 99

Text #15

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1958169 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4504. Min Act: -0.0000

Data Index: 157855 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4496. Min Act: -0.0000

Data Index: 663093 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1541153 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 0.7087. Min Range: -0.7087

Max Act: 0.4506. Min Act: -0.0000

Data Index: 459250 (The Pile)

Max Activating Token Index: 924