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

Dataset: The Pile

Neuron 1000 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: 5.7382. Min Range: -5.7382

Max Act: 5.7382. Min Act: -0.0000

Data Index: 183251 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.5636. Min Act: -0.0000

Data Index: 476655 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 5.7382. Min Range: -5.7382

Max Act: 5.0205. Min Act: -0.0000

Data Index: 601852 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.7079. Min Act: -0.0000

Data Index: 1103940 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.8651. Min Act: -0.0000

Data Index: 1850675 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.5199. Min Act: -0.0000

Data Index: 1345414 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.3163. Min Act: -0.0000

Data Index: 1672718 (The Pile)

Max Activating Token Index: 620

Text #7

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.7754. Min Act: -0.0000

Data Index: 420406 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.1434. Min Act: -0.0000

Data Index: 1654385 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.0821. Min Act: -0.0000

Data Index: 1038943 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.0614. Min Act: 0.0000

Data Index: 1895608 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.0203. Min Act: -0.0000

Data Index: 1847309 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 5.7382. Min Range: -5.7382

Max Act: 3.9940. Min Act: -0.0000

Data Index: 1020094 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 5.7382. Min Range: -5.7382

Max Act: 3.9724. Min Act: -0.0000

Data Index: 363005 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.1922. Min Act: -0.0000

Data Index: 1552590 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 5.7382. Min Range: -5.7382

Max Act: 4.1815. Min Act: -0.0000

Data Index: 90702 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 5.7382. Min Range: -5.7382

Max Act: 3.9816. Min Act: -0.0000

Data Index: 1680214 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 5.7382. Min Range: -5.7382

Max Act: 3.8161. Min Act: -0.0000

Data Index: 612829 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 5.7382. Min Range: -5.7382

Max Act: 3.9808. Min Act: -0.0000

Data Index: 1029616 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 5.7382. Min Range: -5.7382

Max Act: 3.9795. Min Act: -0.0000

Data Index: 363243 (The Pile)

Max Activating Token Index: 551