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

Dataset: The Pile

Neuron 2770 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: 0.6763. Min Range: -0.6763

Max Act: 0.6223. Min Act: -0.0000

Data Index: 509173 (The Pile)

Max Activating Token Index: 1020

Text #1

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6640. Min Act: -0.0000

Data Index: 356146 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6763. Min Act: -0.0000

Data Index: 273429 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1871016 (The Pile)

Max Activating Token Index: 829

Text #4

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6444. Min Act: -0.0000

Data Index: 934684 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1207891 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6072. Min Act: -0.0000

Data Index: 281943 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6212. Min Act: -0.0000

Data Index: 653146 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6051. Min Act: -0.0000

Data Index: 635399 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6200. Min Act: -0.0000

Data Index: 128695 (The Pile)

Max Activating Token Index: 3

Text #10

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1847225 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1947315 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6175. Min Act: -0.0000

Data Index: 664254 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6169. Min Act: -0.0000

Data Index: 635432 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1831373 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1172044 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5911. Min Act: -0.0000

Data Index: 106192 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6104. Min Act: -0.0000

Data Index: 261467 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.5871. Min Act: -0.0000

Data Index: 706109 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.6763. Min Range: -0.6763

Max Act: 0.6036. Min Act: -0.0000

Data Index: 573546 (The Pile)

Max Activating Token Index: 578