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

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

Neuron 5029 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: 3.4200. Min Range: -3.4200

Max Act: 3.4200. Min Act: -0.0000

Data Index: 1478882 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 3.4200. Min Range: -3.4200

Max Act: 3.0964. Min Act: -0.0000

Data Index: 1525931 (Python Code)

Max Activating Token Index: 691

Text #2

Max Range: 3.4200. Min Range: -3.4200

Max Act: 3.0000. Min Act: -0.0000

Data Index: 1551011 (Python Code)

Max Activating Token Index: 46

Text #3

Max Range: 3.4200. Min Range: -3.4200

Max Act: 3.0916. Min Act: -0.0000

Data Index: 1398485 (Python Code)

Max Activating Token Index: 566

Text #4

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.9010. Min Act: -0.0000

Data Index: 1515392 (Python Code)

Max Activating Token Index: 493

Text #5

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.6047. Min Act: -0.0000

Data Index: 1392123 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.6964. Min Act: -0.0000

Data Index: 1484238 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.5540. Min Act: -0.0000

Data Index: 1534555 (Python Code)

Max Activating Token Index: 103

Text #8

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.5425. Min Act: -0.0000

Data Index: 1529518 (Python Code)

Max Activating Token Index: 151

Text #9

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.6386. Min Act: -0.0000

Data Index: 1515849 (Python Code)

Max Activating Token Index: 967

Text #10

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.4859. Min Act: -0.0000

Data Index: 1364176 (Python Code)

Max Activating Token Index: 924

Text #11

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.4878. Min Act: -0.0000

Data Index: 1581126 (Python Code)

Max Activating Token Index: 384

Text #12

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1405596 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.3809. Min Act: -0.0000

Data Index: 1650014 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.3616. Min Act: -0.0000

Data Index: 1644685 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.6125. Min Act: -0.0000

Data Index: 1522588 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.2268. Min Act: -0.0000

Data Index: 1413380 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.5916. Min Act: -0.0000

Data Index: 1573461 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.4533. Min Act: -0.0000

Data Index: 1371528 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 3.4200. Min Range: -3.4200

Max Act: 2.5681. Min Act: -0.0000

Data Index: 1433958 (Python Code)

Max Activating Token Index: 640