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

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

Neuron 5099 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.7572. Min Act: -0.0000

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.6789. Min Act: -0.0000

Data Index: 716804 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 1.7572. Min Range: -1.7572

Max Act: 1.0034. Min Act: -0.0000

Data Index: 195766 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.7095. Min Act: -0.0000

Data Index: 301047 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1060416 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.4862. Min Act: -0.0000

Data Index: 13388 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.3541. Min Act: -0.0000

Data Index: 110337 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.3191. Min Act: -0.0000

Data Index: 634311 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2928. Min Act: -0.0000

Data Index: 757427 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2765. Min Act: -0.0000

Data Index: 899362 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2602. Min Act: -0.0000

Data Index: 250633 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2469. Min Act: -0.0000

Data Index: 432922 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2397. Min Act: -0.0000

Data Index: 544041 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2282. Min Act: -0.0000

Data Index: 889415 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2346. Min Act: -0.0000

Data Index: 656287 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2359. Min Act: -0.0000

Data Index: 243054 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2236. Min Act: -0.0000

Data Index: 159901 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2274. Min Act: -0.0000

Data Index: 170906 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1103856 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.7572. Min Range: -1.7572

Max Act: 0.2238. Min Act: -0.0000

Data Index: 99924 (C4 (Web Text))

Max Activating Token Index: 521