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

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

Neuron 3942 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2737. Min Range: -1.2737

Max Act: 1.2737. Min Act: -0.0000

Data Index: 372177 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.9629. Min Act: -0.0000

Data Index: 617782 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.6720. Min Act: -0.0000

Data Index: 967192 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7119. Min Act: -0.0000

Data Index: 754780 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7026. Min Act: -0.0000

Data Index: 126026 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1271749 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.6532. Min Act: -0.0000

Data Index: 317609 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.5915. Min Act: -0.0000

Data Index: 486071 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1191150 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1300841 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.5226. Min Act: -0.0000

Data Index: 206017 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.4966. Min Act: -0.0000

Data Index: 582516 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1188084 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.4359. Min Act: -0.0000

Data Index: 12623 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.4568. Min Act: -0.0000

Data Index: 741177 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.3927. Min Act: -0.0000

Data Index: 81444 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1358672 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1330600 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1253614 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1279576 (C4 (Web Text))

Max Activating Token Index: 970