Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1584 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1873. Min Act: -0.0001

Data Index: 674751 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1895. Min Act: -0.0000

Data Index: 966895 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1790. Min Act: -0.0000

Data Index: 452136 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1623042 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1708. Min Act: -0.0000

Data Index: 35143 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1671. Min Act: -0.0001

Data Index: 96644 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1661. Min Act: -0.0001

Data Index: 681806 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1479. Min Act: -0.0001

Data Index: 79288 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1503. Min Act: -0.0000

Data Index: 872194 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1593. Min Act: -0.0001

Data Index: 202125 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1583. Min Act: -0.0001

Data Index: 1010147 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1017562 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1318835 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1286443 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1533. Min Act: -0.0001

Data Index: 444903 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1430. Min Act: -0.0000

Data Index: 845137 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1373. Min Act: -0.0000

Data Index: 209059 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1359240 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1399. Min Act: -0.0001

Data Index: 69500 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1386. Min Act: -0.0000

Data Index: 347234 (C4 (Web Text))

Max Activating Token Index: 168