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

Dataset: The Pile

Neuron 4031 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.5315. Min Act: -0.0000

Data Index: 196153 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.5167. Min Act: -0.0000

Data Index: 419972 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.5248. Min Act: -0.0000

Data Index: 241557 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.5099. Min Act: -0.0000

Data Index: 568236 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1446115 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1091559 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.5251. Min Act: -0.0000

Data Index: 922179 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1938519 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4761. Min Act: -0.0000

Data Index: 312831 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1181599 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4852. Min Act: -0.0000

Data Index: 904454 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1269523 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1804583 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1465700 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4269. Min Act: -0.0000

Data Index: 837400 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1488403 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4506. Min Act: -0.0000

Data Index: 627752 (The Pile)

Max Activating Token Index: 467

Text #17

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4479. Min Act: -0.0000

Data Index: 596048 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1920367 (The Pile)

Max Activating Token Index: 505

Text #19

Max Range: 0.5315. Min Range: -0.5315

Max Act: 0.4271. Min Act: -0.0000

Data Index: 18960 (The Pile)

Max Activating Token Index: 109