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

Dataset: The Pile

Neuron 2517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6141. Min Range: -1.6141

Max Act: 1.6141. Min Act: -0.0000

Data Index: 1923703 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 1.6141. Min Range: -1.6141

Max Act: 1.3066. Min Act: -0.0000

Data Index: 55350 (The Pile)

Max Activating Token Index: 481

Text #2

Max Range: 1.6141. Min Range: -1.6141

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1592529 (The Pile)

Max Activating Token Index: 576

Text #3

Max Range: 1.6141. Min Range: -1.6141

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1030226 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 1.6141. Min Range: -1.6141

Max Act: 1.1957. Min Act: -0.0000

Data Index: 1376382 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 1.6141. Min Range: -1.6141

Max Act: 1.0482. Min Act: -0.0000

Data Index: 239093 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.9509. Min Act: -0.0000

Data Index: 515082 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1056650 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1931795 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1877 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1215747 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.8507. Min Act: -0.0000

Data Index: 774414 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1752332 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7727. Min Act: -0.0000

Data Index: 758203 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7280. Min Act: -0.0000

Data Index: 987208 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7418. Min Act: -0.0000

Data Index: 959829 (The Pile)

Max Activating Token Index: 336

Text #16

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7145. Min Act: -0.0000

Data Index: 629565 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1719351 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.6922. Min Act: -0.0000

Data Index: 640988 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.6141. Min Range: -1.6141

Max Act: 0.7482. Min Act: -0.0000

Data Index: 601070 (The Pile)

Max Activating Token Index: 739