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

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

Neuron 3244 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0447. Min Range: -1.0447

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1194609 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7827. Min Act: -0.0000

Data Index: 880185 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7706. Min Act: -0.0000

Data Index: 225835 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7660. Min Act: -0.0000

Data Index: 458223 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7721. Min Act: -0.0000

Data Index: 965398 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7085. Min Act: -0.0000

Data Index: 464307 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.7586. Min Act: -0.0000

Data Index: 72320 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6941. Min Act: -0.0000

Data Index: 721545 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6819. Min Act: -0.0000

Data Index: 399576 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1040977 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6568. Min Act: -0.0000

Data Index: 416759 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6754. Min Act: -0.0000

Data Index: 900621 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6442. Min Act: -0.0000

Data Index: 585560 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6398. Min Act: -0.0000

Data Index: 505574 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1039393 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6362. Min Act: -0.0000

Data Index: 195342 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.5991. Min Act: -0.0000

Data Index: 670774 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6028. Min Act: -0.0000

Data Index: 677570 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.6114. Min Act: -0.0000

Data Index: 455287 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 1.0447. Min Range: -1.0447

Max Act: 0.5885. Min Act: 0.0000

Data Index: 1346583 (C4 (Web Text))

Max Activating Token Index: 917