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

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

Neuron 574 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: 5.6490. Min Range: -5.6490

Max Act: 5.5992. Min Act: -0.0000

Data Index: 398250 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.2821. Min Act: -0.0000

Data Index: 238660 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.6490. Min Act: -0.0000

Data Index: 353093 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.2431. Min Act: -0.0000

Data Index: 34180 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.5707. Min Act: -0.0000

Data Index: 857503 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.0258. Min Act: -0.0000

Data Index: 846404 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.8180. Min Act: -0.0000

Data Index: 1036762 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.0373. Min Act: -0.0000

Data Index: 1093333 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.1547. Min Act: -0.0000

Data Index: 241645 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.9708. Min Act: -0.0000

Data Index: 694585 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.9775. Min Act: -0.0000

Data Index: 862388 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.9309. Min Act: -0.0000

Data Index: 851599 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.9153. Min Act: -0.0000

Data Index: 359313 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.7328. Min Act: -0.0000

Data Index: 37631 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.8899. Min Act: -0.0000

Data Index: 413754 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.0005. Min Act: -0.0000

Data Index: 1258651 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.8121. Min Act: -0.0000

Data Index: 329499 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.7819. Min Act: -0.0000

Data Index: 1263784 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 5.6490. Min Range: -5.6490

Max Act: 5.2631. Min Act: -0.0000

Data Index: 1115172 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 5.6490. Min Range: -5.6490

Max Act: 4.7287. Min Act: -0.0000

Data Index: 1347451 (C4 (Web Text))

Max Activating Token Index: 905