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

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

Neuron 4938 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.6877. Min Act: -0.0000

Data Index: 615389 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1311387 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.6048. Min Act: -0.0000

Data Index: 374 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.6142. Min Act: -0.0000

Data Index: 340249 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.6046. Min Act: -0.0000

Data Index: 959602 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5799. Min Act: -0.0000

Data Index: 364555 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5940. Min Act: -0.0000

Data Index: 562507 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5742. Min Act: -0.0000

Data Index: 944668 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5965. Min Act: -0.0000

Data Index: 971953 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5620. Min Act: -0.0000

Data Index: 902826 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5495. Min Act: -0.0000

Data Index: 217438 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5181. Min Act: -0.0000

Data Index: 976113 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5092. Min Act: -0.0000

Data Index: 220091 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5072. Min Act: -0.0000

Data Index: 695378 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5664. Min Act: -0.0000

Data Index: 666048 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5358. Min Act: -0.0000

Data Index: 376123 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5373. Min Act: -0.0000

Data Index: 122101 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1114240 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1098114 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.6877. Min Range: -0.6877

Max Act: 0.5588. Min Act: -0.0000

Data Index: 738671 (C4 (Web Text))

Max Activating Token Index: 197