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

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

Neuron 3226 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4229. Min Range: -1.4229

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1263091 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.4229. Min Range: -1.4229

Max Act: 1.4229. Min Act: -0.0000

Data Index: 638909 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.9676. Min Act: -0.0000

Data Index: 92014 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.9351. Min Act: -0.0000

Data Index: 847983 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1214995 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.8673. Min Act: -0.0000

Data Index: 244115 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1210505 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1229080 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1182702 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.8424. Min Act: -0.0000

Data Index: 816795 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.7606. Min Act: -0.0000

Data Index: 876694 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.7596. Min Act: -0.0000

Data Index: 580400 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.7027. Min Act: -0.0000

Data Index: 122357 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.6944. Min Act: -0.0000

Data Index: 110161 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1241533 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.7183. Min Act: -0.0000

Data Index: 359265 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.7853. Min Act: -0.0000

Data Index: 975661 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.7308. Min Act: -0.0000

Data Index: 317839 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1427223 (Python Code)

Max Activating Token Index: 446

Text #19

Max Range: 1.4229. Min Range: -1.4229

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1031986 (C4 (Web Text))

Max Activating Token Index: 837