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

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

Neuron 5748 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.7778. Min Act: -0.0000

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.7821. Min Act: -0.0000

Data Index: 729778 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5812. Min Act: -0.0000

Data Index: 1480134 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5749. Min Act: -0.0000

Data Index: 1563300 (Python Code)

Max Activating Token Index: 920

Text #4

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.6909. Min Act: -0.0000

Data Index: 456675 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5469. Min Act: -0.0000

Data Index: 1084334 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.6434. Min Act: -0.0000

Data Index: 275232 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5655. Min Act: -0.0000

Data Index: 1630917 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5155. Min Act: -0.0000

Data Index: 622447 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1553715 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1213631 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5031. Min Act: -0.0000

Data Index: 485449 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1595888 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3807. Min Act: -0.0000

Data Index: 1577735 (Python Code)

Max Activating Token Index: 137

Text #14

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1599448 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4313. Min Act: -0.0000

Data Index: 1452815 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1449894 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4597. Min Act: -0.0000

Data Index: 354178 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4380. Min Act: -0.0000

Data Index: 927993 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.4277. Min Act: -0.0000

Data Index: 622237 (C4 (Web Text))

Max Activating Token Index: 409