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

Dataset: The Pile

Neuron 104 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: 0.9310. Min Range: -0.9310

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1533697 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1521537 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1281086 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1630079 (The Pile)

Max Activating Token Index: 884

Text #4

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7338. Min Act: -0.0000

Data Index: 970156 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.7395. Min Act: -0.0000

Data Index: 414091 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1606102 (The Pile)

Max Activating Token Index: 842

Text #7

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1785760 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1581535 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6236. Min Act: 0.0000

Data Index: 375597 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1833178 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1994623 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1381287 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1767102 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1125425 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5587. Min Act: -0.0000

Data Index: 578054 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1685417 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1959346 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1314305 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 0.9310. Min Range: -0.9310

Max Act: 0.5239. Min Act: 0.0000

Data Index: 1739303 (The Pile)

Max Activating Token Index: 702