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

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

Neuron 739 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.7806. Min Act: -0.0001

Data Index: 1635462 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.7768. Min Act: -0.0001

Data Index: 1467554 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.6187. Min Act: -0.0002

Data Index: 1534363 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.7214. Min Act: -0.0001

Data Index: 1595116 (Python Code)

Max Activating Token Index: 491

Text #4

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.6842. Min Act: -0.0001

Data Index: 1453104 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4673. Min Act: -0.0001

Data Index: 1490096 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.6348. Min Act: -0.0001

Data Index: 1524669 (Python Code)

Max Activating Token Index: 685

Text #7

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4528. Min Act: -0.0001

Data Index: 656221 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.5316. Min Act: -0.0001

Data Index: 1411452 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.5357. Min Act: -0.0001

Data Index: 1490993 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.5220. Min Act: -0.0001

Data Index: 1556746 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.5065. Min Act: -0.0002

Data Index: 349501 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4663. Min Act: -0.0001

Data Index: 1489612 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.1464. Min Act: -0.0001

Data Index: 485345 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4060. Min Act: -0.0001

Data Index: 514460 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.4764. Min Act: -0.0002

Data Index: 915765 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.2069. Min Act: -0.0001

Data Index: 451551 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3649. Min Act: -0.0001

Data Index: 1234609 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3845. Min Act: -0.0001

Data Index: 945922 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 1.7806. Min Range: -1.7806

Max Act: 1.3988. Min Act: -0.0001

Data Index: 1205421 (C4 (Web Text))

Max Activating Token Index: 740