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

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

Neuron 5085 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.8784. Min Act: -0.0000

Data Index: 1482374 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.7204. Min Act: 0.0001

Data Index: 1643265 (Python Code)

Max Activating Token Index: 672

Text #2

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.8120. Min Act: 0.0001

Data Index: 1614171 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.5977. Min Act: 0.0001

Data Index: 1561077 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3771. Min Act: 0.0000

Data Index: 1526228 (Python Code)

Max Activating Token Index: 789

Text #5

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.4455. Min Act: -0.0000

Data Index: 1421924 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3854. Min Act: 0.0000

Data Index: 1578850 (Python Code)

Max Activating Token Index: 812

Text #7

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3826. Min Act: 0.0001

Data Index: 1435822 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1516271 (Python Code)

Max Activating Token Index: 949

Text #9

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3978. Min Act: 0.0001

Data Index: 1616180 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.4379. Min Act: 0.0001

Data Index: 1605863 (Python Code)

Max Activating Token Index: 694

Text #11

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3720. Min Act: -0.0000

Data Index: 1380324 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.3752. Min Act: 0.0001

Data Index: 1418859 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.2827. Min Act: 0.0001

Data Index: 1608972 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.2200. Min Act: 0.0001

Data Index: 1447095 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.2496. Min Act: 0.0001

Data Index: 1461020 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1573516 (Python Code)

Max Activating Token Index: 371

Text #17

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1710. Min Act: 0.0001

Data Index: 1505060 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.1442. Min Act: 0.0001

Data Index: 1566253 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 1.8784. Min Range: -1.8784

Max Act: 1.0736. Min Act: 0.0001

Data Index: 1557480 (Python Code)

Max Activating Token Index: 398