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

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

Neuron 1528 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1029. Min Range: -4.1029

Max Act: 4.1029. Min Act: -0.0000

Data Index: 218784 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.1368. Min Act: -0.0000

Data Index: 1145530 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 4.1029. Min Range: -4.1029

Max Act: 3.0283. Min Act: -0.0000

Data Index: 278577 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.9453. Min Act: -0.0000

Data Index: 793862 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.8085. Min Act: 0.0000

Data Index: 53041 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.6566. Min Act: -0.0000

Data Index: 186405 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.5931. Min Act: -0.0000

Data Index: 1328607 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.8102. Min Act: -0.0000

Data Index: 678092 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.3710. Min Act: -0.0000

Data Index: 126158 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.5695. Min Act: -0.0000

Data Index: 519982 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.0715. Min Act: -0.0000

Data Index: 32739 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.4056. Min Act: -0.0000

Data Index: 415821 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1042733 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.3993. Min Act: -0.0000

Data Index: 225177 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.3870. Min Act: -0.0000

Data Index: 641890 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.3443. Min Act: -0.0000

Data Index: 364233 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.2235. Min Act: -0.0000

Data Index: 233320 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.2124. Min Act: -0.0000

Data Index: 391322 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 4.1029. Min Range: -4.1029

Max Act: 2.4148. Min Act: -0.0000

Data Index: 854729 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 4.1029. Min Range: -4.1029

Max Act: 1.9459. Min Act: -0.0000

Data Index: 406724 (C4 (Web Text))

Max Activating Token Index: 270