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

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

Neuron 3990 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.4239. Min Act: -0.0002

Data Index: 973681 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.3729. Min Act: -0.0001

Data Index: 314260 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.3667. Min Act: -0.0002

Data Index: 1120769 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.3389. Min Act: -0.0002

Data Index: 1065387 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.3655. Min Act: -0.0001

Data Index: 1065714 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.3801. Min Act: -0.0001

Data Index: 891492 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2033. Min Act: -0.0002

Data Index: 465952 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2642. Min Act: -0.0002

Data Index: 1191782 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2800. Min Act: -0.0002

Data Index: 265040 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2083. Min Act: -0.0002

Data Index: 1350536 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1931. Min Act: -0.0002

Data Index: 1274727 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1932. Min Act: -0.0002

Data Index: 1192093 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2198. Min Act: -0.0001

Data Index: 1295623 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1780. Min Act: -0.0001

Data Index: 27785 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1774. Min Act: -0.0002

Data Index: 787720 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2537. Min Act: -0.0001

Data Index: 196014 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1949. Min Act: -0.0001

Data Index: 699258 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.2203. Min Act: -0.0001

Data Index: 354520 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1472. Min Act: -0.0002

Data Index: 594353 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 1.4239. Min Range: -1.4239

Max Act: 1.1352. Min Act: -0.0002

Data Index: 1212663 (C4 (Web Text))

Max Activating Token Index: 960