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

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

Neuron 2479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0321. Min Act: -0.0001

Data Index: 225542 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.0333. Min Range: -1.0333

Max Act: 1.0333. Min Act: -0.0000

Data Index: 327552 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1381890 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8301. Min Act: -0.0001

Data Index: 239608 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1225869 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1176021 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1481594 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7782. Min Act: -0.0001

Data Index: 1212901 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7572. Min Act: -0.0000

Data Index: 50225 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7384. Min Act: -0.0000

Data Index: 895069 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.6652. Min Act: -0.0000

Data Index: 64314 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7863. Min Act: -0.0001

Data Index: 123066 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.6777. Min Act: -0.0000

Data Index: 400032 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7649. Min Act: -0.0001

Data Index: 1204699 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7114. Min Act: -0.0000

Data Index: 331306 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.6638. Min Act: -0.0001

Data Index: 1415200 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1049715 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1471313 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 1.0333. Min Range: -1.0333

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1318904 (C4 (Web Text))

Max Activating Token Index: 581