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

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

Neuron 1469 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0511. Min Range: -2.0511

Max Act: 2.0511. Min Act: -0.0000

Data Index: 292349 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.8747. Min Act: -0.0000

Data Index: 270854 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1297856 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.6496. Min Act: -0.0000

Data Index: 782683 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.7613. Min Act: -0.0000

Data Index: 534679 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.8200. Min Act: -0.0000

Data Index: 537764 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1421494 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.7076. Min Act: -0.0000

Data Index: 815775 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.7054. Min Act: -0.0000

Data Index: 1084610 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.5962. Min Act: -0.0000

Data Index: 850738 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.6212. Min Act: -0.0000

Data Index: 61230 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1396477 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1128711 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.4379. Min Act: -0.0000

Data Index: 1652807 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.7184. Min Act: -0.0000

Data Index: 1607248 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1422400 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.5611. Min Act: -0.0000

Data Index: 72742 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.7083. Min Act: -0.0000

Data Index: 1605003 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1066331 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 2.0511. Min Range: -2.0511

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1411701 (Python Code)

Max Activating Token Index: 87