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

Dataset: The Pile

Neuron 646 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: 0.6945. Min Range: -0.6945

Max Act: 0.6945. Min Act: -0.0000

Data Index: 168329 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1004232 (The Pile)

Max Activating Token Index: 531

Text #2

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6072. Min Act: -0.0000

Data Index: 895773 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5884. Min Act: 0.0000

Data Index: 1826944 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1916441 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5583. Min Act: 0.0000

Data Index: 337166 (The Pile)

Max Activating Token Index: 109

Text #6

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5608. Min Act: -0.0000

Data Index: 729340 (The Pile)

Max Activating Token Index: 117

Text #7

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1323354 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5279. Min Act: -0.0000

Data Index: 205066 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5437. Min Act: -0.0000

Data Index: 19903 (The Pile)

Max Activating Token Index: 402

Text #10

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1400080 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5489. Min Act: -0.0000

Data Index: 1120162 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1781596 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1380816 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5228. Min Act: -0.0000

Data Index: 222247 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5398. Min Act: -0.0000

Data Index: 237149 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5538. Min Act: -0.0000

Data Index: 73957 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5397. Min Act: -0.0000

Data Index: 547699 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5034. Min Act: -0.0000

Data Index: 145499 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5029. Min Act: -0.0000

Data Index: 852917 (The Pile)

Max Activating Token Index: 913