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

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

Neuron 3590 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.8854. Min Act: -0.0001

Data Index: 1497908 (Python Code)

Max Activating Token Index: 728

Text #1

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.8632. Min Act: -0.0001

Data Index: 1491718 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.8605. Min Act: -0.0001

Data Index: 1545526 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.7083. Min Act: -0.0001

Data Index: 1571183 (Python Code)

Max Activating Token Index: 458

Text #4

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.7977. Min Act: -0.0001

Data Index: 1590777 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.6847. Min Act: -0.0001

Data Index: 1542607 (Python Code)

Max Activating Token Index: 997

Text #6

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.6117. Min Act: -0.0001

Data Index: 1392049 (Python Code)

Max Activating Token Index: 672

Text #7

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.6447. Min Act: -0.0001

Data Index: 1653613 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5895. Min Act: -0.0001

Data Index: 1381016 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5909. Min Act: -0.0001

Data Index: 1610331 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4774. Min Act: -0.0001

Data Index: 1495709 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4244. Min Act: -0.0001

Data Index: 1603628 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4208. Min Act: -0.0001

Data Index: 1552970 (Python Code)

Max Activating Token Index: 274

Text #13

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4441. Min Act: -0.0001

Data Index: 1467660 (Python Code)

Max Activating Token Index: 131

Text #14

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4016. Min Act: -0.0001

Data Index: 1564190 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4717. Min Act: -0.0001

Data Index: 1648229 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.3487. Min Act: -0.0001

Data Index: 1644807 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4177. Min Act: -0.0001

Data Index: 1516092 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4208. Min Act: -0.0001

Data Index: 1460515 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4503. Min Act: -0.0001

Data Index: 1361224 (Python Code)

Max Activating Token Index: 487