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

Dataset: The Pile

Neuron 1359 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1978. Min Range: -1.1978

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1856839 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 1.1978. Min Range: -1.1978

Max Act: 1.1160. Min Act: -0.0000

Data Index: 273257 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 1.1978. Min Range: -1.1978

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1215316 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8746. Min Act: -0.0000

Data Index: 1287364 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.9158. Min Act: -0.0000

Data Index: 991010 (The Pile)

Max Activating Token Index: 215

Text #5

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1965021 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1693805 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1958363 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8737. Min Act: -0.0000

Data Index: 387725 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.9036. Min Act: -0.0000

Data Index: 416419 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1692172 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7969. Min Act: -0.0000

Data Index: 861849 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8416. Min Act: -0.0000

Data Index: 560956 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7852. Min Act: -0.0000

Data Index: 348067 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8616. Min Act: -0.0000

Data Index: 671306 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1083306 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1952728 (The Pile)

Max Activating Token Index: 553

Text #17

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.8110. Min Act: -0.0000

Data Index: 910091 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7980. Min Act: -0.0000

Data Index: 344939 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 1.1978. Min Range: -1.1978

Max Act: 0.7982. Min Act: -0.0000

Data Index: 787179 (The Pile)

Max Activating Token Index: 476