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

Dataset: The Pile

Neuron 3390 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: 10.6397. Min Range: -10.6397

Max Act: 10.6397. Min Act: -0.0000

Data Index: 1640519 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 10.6397. Min Range: -10.6397

Max Act: 9.4857. Min Act: -0.0000

Data Index: 1205557 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 10.6397. Min Range: -10.6397

Max Act: 9.5957. Min Act: -0.0000

Data Index: 1335212 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 10.6397. Min Range: -10.6397

Max Act: 9.2292. Min Act: -0.0000

Data Index: 970398 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 10.6397. Min Range: -10.6397

Max Act: 9.0734. Min Act: -0.0000

Data Index: 324939 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.4536. Min Act: -0.0000

Data Index: 1821490 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 10.6397. Min Range: -10.6397

Max Act: 9.1048. Min Act: -0.0000

Data Index: 691237 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.9302. Min Act: -0.0000

Data Index: 755527 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 10.6397. Min Range: -10.6397

Max Act: 7.3375. Min Act: -0.0000

Data Index: 25577 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.4113. Min Act: -0.0000

Data Index: 36609 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 10.6397. Min Range: -10.6397

Max Act: 7.6344. Min Act: -0.0000

Data Index: 1701056 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 10.6397. Min Range: -10.6397

Max Act: 7.9741. Min Act: -0.0000

Data Index: 1559228 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.0120. Min Act: -0.0000

Data Index: 797576 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.4816. Min Act: -0.0000

Data Index: 631726 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.4189. Min Act: -0.0000

Data Index: 382422 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.1232. Min Act: -0.0000

Data Index: 386765 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.4010. Min Act: -0.0000

Data Index: 431725 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.1233. Min Act: -0.0000

Data Index: 463645 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.1239. Min Act: -0.0000

Data Index: 259926 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 10.6397. Min Range: -10.6397

Max Act: 8.6476. Min Act: -0.0000

Data Index: 555458 (The Pile)

Max Activating Token Index: 554