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

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

Neuron 3244 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2739. Min Act: -0.0000

Data Index: 876459 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2452. Min Act: -0.0000

Data Index: 154923 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2302. Min Act: -0.0000

Data Index: 617279 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2099. Min Act: -0.0000

Data Index: 166677 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1935. Min Act: -0.0000

Data Index: 292208 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1925. Min Act: -0.0000

Data Index: 670119 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1977. Min Act: -0.0000

Data Index: 1058525 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1031106 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1133919 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1771. Min Act: -0.0000

Data Index: 643333 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1627. Min Act: -0.0000

Data Index: 340889 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1716. Min Act: -0.0000

Data Index: 888962 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1691. Min Act: -0.0000

Data Index: 211729 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1682. Min Act: -0.0000

Data Index: 761838 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1104735 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1451. Min Act: -0.0000

Data Index: 334377 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1540. Min Act: -0.0000

Data Index: 621732 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1585. Min Act: -0.0000

Data Index: 409699 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1039577 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1581. Min Act: -0.0000

Data Index: 834413 (C4 (Web Text))

Max Activating Token Index: 233