Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3965 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.8270. Min Act: -0.0003

Data Index: 980806 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6966. Min Act: -0.0002

Data Index: 1358091 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6865. Min Act: -0.0003

Data Index: 189067 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6834. Min Act: -0.0003

Data Index: 451188 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6768. Min Act: -0.0002

Data Index: 232393 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6760. Min Act: -0.0002

Data Index: 523974 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6683. Min Act: -0.0002

Data Index: 435849 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6608. Min Act: -0.0002

Data Index: 624964 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6594. Min Act: -0.0002

Data Index: 198023 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6514. Min Act: -0.0002

Data Index: 47453 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6490. Min Act: -0.0003

Data Index: 889281 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6477. Min Act: -0.0002

Data Index: 1080094 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6349. Min Act: -0.0002

Data Index: 1195568 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6306. Min Act: -0.0002

Data Index: 571546 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6286. Min Act: -0.0002

Data Index: 1189459 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6288. Min Act: -0.0003

Data Index: 665890 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6268. Min Act: -0.0003

Data Index: 1087482 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5718. Min Act: -0.0002

Data Index: 302493 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5697. Min Act: -0.0002

Data Index: 207866 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.6062. Min Act: -0.0002

Data Index: 977820 (C4 (Web Text))

Max Activating Token Index: 901