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

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

Neuron 5266 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.6373. Min Act: -0.0000

Data Index: 727308 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.1454. Min Act: -0.0000

Data Index: 1001984 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.0115. Min Act: -0.0000

Data Index: 833134 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.1453. Min Act: -0.0000

Data Index: 582285 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.1386. Min Act: -0.0000

Data Index: 390874 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.1162. Min Act: -0.0000

Data Index: 1147908 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.2674. Min Act: -0.0000

Data Index: 927205 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.9326. Min Act: -0.0000

Data Index: 338860 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.0765. Min Act: -0.0000

Data Index: 912701 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.9256. Min Act: -0.0000

Data Index: 1242605 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 3.6373. Min Range: -3.6373

Max Act: 3.0700. Min Act: -0.0000

Data Index: 78994 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.9748. Min Act: -0.0000

Data Index: 1304537 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.9784. Min Act: -0.0000

Data Index: 908546 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.8069. Min Act: -0.0000

Data Index: 1105785 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.9630. Min Act: -0.0000

Data Index: 1245637 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.7824. Min Act: -0.0000

Data Index: 161095 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.9179. Min Act: -0.0000

Data Index: 1260656 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.7409. Min Act: -0.0000

Data Index: 1007516 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.8779. Min Act: -0.0000

Data Index: 818913 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 3.6373. Min Range: -3.6373

Max Act: 2.8528. Min Act: -0.0000

Data Index: 824549 (C4 (Web Text))

Max Activating Token Index: 60