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

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

Neuron 349 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: 1.8990. Min Range: -1.8990

Max Act: 1.8990. Min Act: -0.0000

Data Index: 180423 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.7768. Min Act: -0.0000

Data Index: 1204766 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.6751. Min Act: -0.0000

Data Index: 234016 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.6700. Min Act: -0.0000

Data Index: 177312 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.6557. Min Act: -0.0000

Data Index: 382727 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5103. Min Act: -0.0000

Data Index: 101676 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4867. Min Act: -0.0000

Data Index: 854811 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4083. Min Act: -0.0000

Data Index: 621925 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4823. Min Act: -0.0000

Data Index: 916405 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4375. Min Act: -0.0000

Data Index: 1089562 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4267. Min Act: -0.0000

Data Index: 919184 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4294. Min Act: -0.0000

Data Index: 310136 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1239126 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5056. Min Act: -0.0000

Data Index: 102067 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.5129. Min Act: -0.0000

Data Index: 174490 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4017. Min Act: -0.0000

Data Index: 1207679 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4700. Min Act: -0.0000

Data Index: 951278 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.4008. Min Act: -0.0000

Data Index: 93015 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1046602 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.8990. Min Range: -1.8990

Max Act: 1.3755. Min Act: -0.0000

Data Index: 86492 (C4 (Web Text))

Max Activating Token Index: 313