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

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

Neuron 4645 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: 2.0033. Min Range: -2.0033

Max Act: 2.0033. Min Act: -0.0000

Data Index: 446180 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.5583. Min Act: -0.0000

Data Index: 30132 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.4689. Min Act: -0.0000

Data Index: 1332045 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.4539. Min Act: -0.0000

Data Index: 405699 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1228578 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.1524. Min Act: -0.0000

Data Index: 1597439 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.1559. Min Act: -0.0000

Data Index: 674234 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1548921 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1400097 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1528699 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1517664 (Python Code)

Max Activating Token Index: 305

Text #11

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.1318. Min Act: -0.0000

Data Index: 906729 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 2.0033. Min Range: -2.0033

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1367609 (Python Code)

Max Activating Token Index: 570

Text #13

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.0631. Min Act: -0.0000

Data Index: 999300 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1519015 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1511679 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1539216 (Python Code)

Max Activating Token Index: 889

Text #17

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.0200. Min Act: -0.0000

Data Index: 485678 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 2.0033. Min Range: -2.0033

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1443594 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 2.0033. Min Range: -2.0033

Max Act: 0.9959. Min Act: -0.0000

Data Index: 825502 (C4 (Web Text))

Max Activating Token Index: 567