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

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

Neuron 1320 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0836. Min Range: -2.0836

Max Act: 2.0628. Min Act: -0.0000

Data Index: 1494687 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 2.0836. Min Range: -2.0836

Max Act: 2.0427. Min Act: -0.0000

Data Index: 57067 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 2.0836. Min Range: -2.0836

Max Act: 2.0836. Min Act: 0.0000

Data Index: 848148 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.9385. Min Act: -0.0000

Data Index: 1391348 (Python Code)

Max Activating Token Index: 973

Text #4

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.8698. Min Act: -0.0000

Data Index: 1280769 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.9472. Min Act: -0.0000

Data Index: 880269 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.9175. Min Act: -0.0000

Data Index: 1403545 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1247815 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.7433. Min Act: -0.0000

Data Index: 489013 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.8005. Min Act: -0.0000

Data Index: 1530312 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.6928. Min Act: -0.0000

Data Index: 1431509 (Python Code)

Max Activating Token Index: 805

Text #11

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.5952. Min Act: -0.0000

Data Index: 1596506 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.7750. Min Act: -0.0000

Data Index: 1296200 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.6787. Min Act: -0.0000

Data Index: 1563292 (Python Code)

Max Activating Token Index: 101

Text #14

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.7127. Min Act: 0.0000

Data Index: 436839 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1463175 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1435566 (Python Code)

Max Activating Token Index: 1010

Text #17

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.6798. Min Act: -0.0000

Data Index: 1573116 (Python Code)

Max Activating Token Index: 426

Text #18

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1632080 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 2.0836. Min Range: -2.0836

Max Act: 1.4786. Min Act: -0.0000

Data Index: 233422 (C4 (Web Text))

Max Activating Token Index: 143