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

Dataset: The Pile

Neuron 2870 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1849758 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1059929 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.1346. Min Act: -0.0000

Data Index: 201017 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0496. Min Act: -0.0000

Data Index: 701580 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0350. Min Act: -0.0000

Data Index: 515571 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1040317 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1742546 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.9076. Min Act: -0.0000

Data Index: 546371 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1666779 (The Pile)

Max Activating Token Index: 571

Text #9

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0504. Min Act: -0.0000

Data Index: 461569 (The Pile)

Max Activating Token Index: 999

Text #10

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1562470 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.9468. Min Act: -0.0000

Data Index: 665190 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 1.2367. Min Range: -1.2367

Max Act: 1.0250. Min Act: -0.0000

Data Index: 371691 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1033301 (The Pile)

Max Activating Token Index: 290

Text #14

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1213562 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.8760. Min Act: -0.0000

Data Index: 429071 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1117960 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1674266 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.8239. Min Act: -0.0000

Data Index: 522268 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 1.2367. Min Range: -1.2367

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1269340 (The Pile)

Max Activating Token Index: 251