Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3941 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0908. Min Range: -1.0908

Max Act: 1.0112. Min Act: -0.0002

Data Index: 1571204 (Python Code)

Max Activating Token Index: 719

Text #1

Max Range: 1.0908. Min Range: -1.0908

Max Act: 1.0734. Min Act: -0.0002

Data Index: 1406211 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9958. Min Act: -0.0002

Data Index: 1442036 (Python Code)

Max Activating Token Index: 385

Text #3

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9752. Min Act: -0.0002

Data Index: 1388515 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9406. Min Act: -0.0002

Data Index: 1438295 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.8365. Min Act: -0.0002

Data Index: 1511924 (Python Code)

Max Activating Token Index: 93

Text #6

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9069. Min Act: -0.0002

Data Index: 1541004 (Python Code)

Max Activating Token Index: 187

Text #7

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9526. Min Act: -0.0002

Data Index: 1362695 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 1.0908. Min Range: -1.0908

Max Act: 1.0381. Min Act: -0.0002

Data Index: 1439048 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.8641. Min Act: -0.0002

Data Index: 1491085 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.8585. Min Act: -0.0002

Data Index: 1495878 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.8706. Min Act: -0.0002

Data Index: 1547922 (Python Code)

Max Activating Token Index: 101

Text #12

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9116. Min Act: -0.0002

Data Index: 1536028 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 1.0908. Min Range: -1.0908

Max Act: 1.0908. Min Act: -0.0002

Data Index: 1587357 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9851. Min Act: -0.0002

Data Index: 1440298 (Python Code)

Max Activating Token Index: 724

Text #15

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9602. Min Act: -0.0002

Data Index: 1412508 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.8684. Min Act: -0.0002

Data Index: 1484095 (Python Code)

Max Activating Token Index: 228

Text #17

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.8568. Min Act: -0.0002

Data Index: 1591338 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9473. Min Act: -0.0002

Data Index: 1364468 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 1.0908. Min Range: -1.0908

Max Act: 0.9079. Min Act: -0.0002

Data Index: 1397744 (Python Code)

Max Activating Token Index: 562