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

Dataset: The Pile

Neuron 677 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: 1.5147. Min Range: -1.5147

Max Act: 1.4468. Min Act: -0.0000

Data Index: 421179 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.4313. Min Act: -0.0000

Data Index: 1158570 (The Pile)

Max Activating Token Index: 348

Text #2

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1164732 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1518285 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.4490. Min Act: 0.0000

Data Index: 686956 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2753. Min Act: -0.0000

Data Index: 948338 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.3392. Min Act: -0.0000

Data Index: 440453 (The Pile)

Max Activating Token Index: 51

Text #7

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1288247 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1535255 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1019481 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2373. Min Act: -0.0000

Data Index: 520906 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.3049. Min Act: -0.0000

Data Index: 949124 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1982222 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1672286 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.2121. Min Act: 0.0000

Data Index: 976332 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.3406. Min Act: -0.0000

Data Index: 729097 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1259980 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.1138. Min Act: -0.0000

Data Index: 375952 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.1091. Min Act: -0.0000

Data Index: 579398 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 1.5147. Min Range: -1.5147

Max Act: 1.1702. Min Act: -0.0000

Data Index: 320586 (The Pile)

Max Activating Token Index: 383