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

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

Neuron 3396 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: 0.8414. Min Range: -0.8414

Max Act: 0.8075. Min Act: -0.0001

Data Index: 1386338 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1416569 (Python Code)

Max Activating Token Index: 876

Text #2

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1456510 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.8138. Min Act: -0.0001

Data Index: 1479510 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7832. Min Act: -0.0001

Data Index: 1470960 (Python Code)

Max Activating Token Index: 551

Text #5

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6979. Min Act: -0.0001

Data Index: 1500005 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1521393 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6946. Min Act: -0.0001

Data Index: 1545085 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1365108 (Python Code)

Max Activating Token Index: 53

Text #9

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6804. Min Act: -0.0001

Data Index: 1528611 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6965. Min Act: -0.0001

Data Index: 1619347 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1561892 (Python Code)

Max Activating Token Index: 1009

Text #12

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.7039. Min Act: -0.0001

Data Index: 1435762 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6595. Min Act: -0.0001

Data Index: 1647371 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1593467 (Python Code)

Max Activating Token Index: 40

Text #15

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6193. Min Act: -0.0001

Data Index: 1451656 (Python Code)

Max Activating Token Index: 865

Text #16

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1386035 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6147. Min Act: -0.0001

Data Index: 1458793 (Python Code)

Max Activating Token Index: 199

Text #18

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6351. Min Act: -0.0001

Data Index: 1577462 (Python Code)

Max Activating Token Index: 588

Text #19

Max Range: 0.8414. Min Range: -0.8414

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1591029 (Python Code)

Max Activating Token Index: 198