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

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

Neuron 2216 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4531. Min Act: -0.0001

Data Index: 364918 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4677. Min Act: -0.0001

Data Index: 390419 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.5072. Min Act: -0.0001

Data Index: 262883 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4952. Min Act: -0.0001

Data Index: 964153 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4937. Min Act: -0.0001

Data Index: 836273 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4636. Min Act: -0.0000

Data Index: 740413 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4329. Min Act: -0.0001

Data Index: 303762 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2614. Min Act: -0.0001

Data Index: 102311 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2610. Min Act: -0.0000

Data Index: 405852 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2700. Min Act: -0.0000

Data Index: 1008733 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2244. Min Act: -0.0000

Data Index: 1211648 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2262. Min Act: -0.0001

Data Index: 931943 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2687. Min Act: -0.0001

Data Index: 345863 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1521. Min Act: -0.0001

Data Index: 1004469 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3068. Min Act: -0.0001

Data Index: 863988 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1162707 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1324406 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1850. Min Act: -0.0001

Data Index: 455573 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1110. Min Act: -0.0000

Data Index: 693115 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1419. Min Act: -0.0001

Data Index: 1323127 (C4 (Web Text))

Max Activating Token Index: 595