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

Dataset: The Pile

Neuron 2269 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: 0.6266. Min Range: -0.6266

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1211205 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1925430 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4825. Min Act: -0.0000

Data Index: 454013 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1745280 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4688. Min Act: -0.0000

Data Index: 930952 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4183. Min Act: -0.0000

Data Index: 693512 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1410603 (The Pile)

Max Activating Token Index: 311

Text #7

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4884. Min Act: -0.0000

Data Index: 929943 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4271. Min Act: -0.0000

Data Index: 176707 (The Pile)

Max Activating Token Index: 433

Text #9

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1061673 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4628. Min Act: -0.0000

Data Index: 627518 (The Pile)

Max Activating Token Index: 957

Text #11

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4101. Min Act: -0.0000

Data Index: 986495 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1892216 (The Pile)

Max Activating Token Index: 679

Text #13

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1238007 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1034468 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1252986 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1581911 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.3742. Min Act: -0.0000

Data Index: 387750 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.3587. Min Act: -0.0000

Data Index: 348942 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 0.6266. Min Range: -0.6266

Max Act: 0.4006. Min Act: -0.0000

Data Index: 62602 (The Pile)

Max Activating Token Index: 789