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

Dataset: The Pile

Neuron 1016 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: 1.8075. Min Range: -1.8075

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1791598 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.8075. Min Act: -0.0000

Data Index: 387041 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1719631 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.4023. Min Act: -0.0000

Data Index: 511681 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.4146. Min Act: -0.0000

Data Index: 223427 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.5101. Min Act: -0.0000

Data Index: 1466435 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1817637 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1553678 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1996044 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.3971. Min Act: -0.0000

Data Index: 1615721 (The Pile)

Max Activating Token Index: 635

Text #10

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.4752. Min Act: -0.0000

Data Index: 854497 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.2385. Min Act: -0.0000

Data Index: 60639 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1361282 (The Pile)

Max Activating Token Index: 205

Text #13

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1536329 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1440590 (The Pile)

Max Activating Token Index: 913

Text #15

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.2700. Min Act: -0.0000

Data Index: 461394 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.3251. Min Act: -0.0000

Data Index: 1989137 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.2684. Min Act: -0.0000

Data Index: 82793 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1966930 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.8075. Min Range: -1.8075

Max Act: 1.2783. Min Act: -0.0000

Data Index: 275249 (The Pile)

Max Activating Token Index: 462