Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3636 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.3465. Min Act: -0.0000

Data Index: 204863 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.2714. Min Act: -0.0000

Data Index: 124937 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.3533. Min Act: -0.0000

Data Index: 1237060 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1714. Min Act: -0.0000

Data Index: 388812 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1660. Min Act: -0.0000

Data Index: 278164 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1567. Min Act: -0.0000

Data Index: 1325813 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1341408 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.1206. Min Act: 0.0000

Data Index: 537875 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1072527 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0652. Min Act: -0.0000

Data Index: 257949 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0647. Min Act: -0.0000

Data Index: 39583 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0100. Min Act: -0.0000

Data Index: 75438 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 1.3533. Min Range: -1.3533

Max Act: 0.9772. Min Act: 0.0000

Data Index: 39446 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1045497 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0214. Min Act: -0.0000

Data Index: 934465 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0064. Min Act: -0.0000

Data Index: 651791 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0055. Min Act: -0.0000

Data Index: 910399 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.3533. Min Range: -1.3533

Max Act: 1.0274. Min Act: -0.0000

Data Index: 563572 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.3533. Min Range: -1.3533

Max Act: 0.9639. Min Act: -0.0000

Data Index: 579384 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 1.3533. Min Range: -1.3533

Max Act: 0.9618. Min Act: -0.0000

Data Index: 809595 (C4 (Web Text))

Max Activating Token Index: 555