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

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

Neuron 577 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.4019. Min Act: -0.0001

Data Index: 1551400 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3719. Min Act: -0.0001

Data Index: 1626310 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1613438 (Python Code)

Max Activating Token Index: 564

Text #3

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3477. Min Act: -0.0001

Data Index: 1566579 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3238. Min Act: -0.0001

Data Index: 1634138 (Python Code)

Max Activating Token Index: 17

Text #5

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1409357 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1421019 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3172. Min Act: -0.0001

Data Index: 1405572 (Python Code)

Max Activating Token Index: 157

Text #8

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3119. Min Act: -0.0001

Data Index: 1579999 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2433. Min Act: -0.0001

Data Index: 1481175 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1408202 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1534624 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1609143 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3349. Min Act: -0.0001

Data Index: 1589293 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3157. Min Act: -0.0001

Data Index: 1434289 (Python Code)

Max Activating Token Index: 4

Text #15

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3048. Min Act: -0.0001

Data Index: 1500355 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1497066 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3129. Min Act: -0.0001

Data Index: 1620709 (Python Code)

Max Activating Token Index: 5

Text #18

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1592407 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 0.4019. Min Range: -0.4019

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1452150 (Python Code)

Max Activating Token Index: 477