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

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

Neuron 442 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3663. Min Range: -2.3663

Max Act: 2.2561. Min Act: -0.0000

Data Index: 223443 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.3663. Min Range: -2.3663

Max Act: 2.3663. Min Act: -0.0000

Data Index: 646071 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 2.3663. Min Range: -2.3663

Max Act: 2.1522. Min Act: -0.0000

Data Index: 595121 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.9940. Min Act: -0.0000

Data Index: 291537 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 2.3663. Min Range: -2.3663

Max Act: 2.0530. Min Act: -0.0000

Data Index: 115972 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.9695. Min Act: -0.0000

Data Index: 139716 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.9741. Min Act: -0.0000

Data Index: 363735 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.9991. Min Act: -0.0000

Data Index: 671873 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.8576. Min Act: -0.0000

Data Index: 504205 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.8318. Min Act: -0.0000

Data Index: 193852 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.7875. Min Act: -0.0000

Data Index: 1548428 (Python Code)

Max Activating Token Index: 477

Text #11

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.7737. Min Act: -0.0000

Data Index: 1012324 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.7737. Min Act: -0.0000

Data Index: 848803 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.8652. Min Act: -0.0000

Data Index: 1030453 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.9847. Min Act: -0.0000

Data Index: 1158010 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1221718 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.7476. Min Act: -0.0000

Data Index: 1173999 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.8049. Min Act: -0.0000

Data Index: 114793 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.7845. Min Act: -0.0000

Data Index: 808018 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 2.3663. Min Range: -2.3663

Max Act: 1.7187. Min Act: -0.0000

Data Index: 129217 (C4 (Web Text))

Max Activating Token Index: 91