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

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

Neuron 3422 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: 1.3563. Min Range: -1.3563

Max Act: 1.3563. Min Act: -0.0000

Data Index: 290200 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.2546. Min Act: 0.0000

Data Index: 215368 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.2209. Min Act: -0.0000

Data Index: 36320 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.2893. Min Act: -0.0000

Data Index: 824282 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.2286. Min Act: -0.0000

Data Index: 345722 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.1872. Min Act: -0.0000

Data Index: 478229 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.1765. Min Act: 0.0000

Data Index: 295771 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.1664. Min Act: -0.0000

Data Index: 817247 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.0854. Min Act: -0.0000

Data Index: 238828 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1183422 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.1016. Min Act: -0.0000

Data Index: 197392 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.0028. Min Act: 0.0000

Data Index: 1046007 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 1.3563. Min Range: -1.3563

Max Act: 0.9698. Min Act: -0.0000

Data Index: 339192 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.0189. Min Act: 0.0000

Data Index: 62507 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.3563. Min Range: -1.3563

Max Act: 0.9818. Min Act: 0.0001

Data Index: 957943 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.3563. Min Range: -1.3563

Max Act: 1.0076. Min Act: -0.0000

Data Index: 646957 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.3563. Min Range: -1.3563

Max Act: 0.9812. Min Act: -0.0000

Data Index: 865290 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 1.3563. Min Range: -1.3563

Max Act: 0.9213. Min Act: 0.0001

Data Index: 506729 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.3563. Min Range: -1.3563

Max Act: 0.8970. Min Act: 0.0000

Data Index: 971968 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.3563. Min Range: -1.3563

Max Act: 0.9558. Min Act: 0.0000

Data Index: 660991 (C4 (Web Text))

Max Activating Token Index: 221