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

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

Neuron 456 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1047. Min Range: -4.1047

Max Act: 4.1047. Min Act: -0.0000

Data Index: 622894 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.6498. Min Act: -0.0000

Data Index: 1057046 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.0733. Min Act: -0.0000

Data Index: 807692 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.3696. Min Act: -0.0000

Data Index: 831271 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.8240. Min Act: -0.0001

Data Index: 444862 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.1789. Min Act: -0.0000

Data Index: 280478 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.1815. Min Act: -0.0001

Data Index: 1358302 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.1430. Min Act: -0.0000

Data Index: 1029019 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.9555. Min Act: -0.0001

Data Index: 995700 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.5516. Min Act: -0.0000

Data Index: 790927 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.1022. Min Act: -0.0001

Data Index: 1017844 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.0718. Min Act: -0.0001

Data Index: 1215699 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.8629. Min Act: -0.0000

Data Index: 31728 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.9567. Min Act: -0.0001

Data Index: 893266 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 4.1047. Min Range: -4.1047

Max Act: 3.1072. Min Act: -0.0001

Data Index: 413929 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.9290. Min Act: -0.0000

Data Index: 1186652 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.9104. Min Act: -0.0000

Data Index: 517226 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.9141. Min Act: -0.0001

Data Index: 450968 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.6439. Min Act: -0.0000

Data Index: 989499 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 4.1047. Min Range: -4.1047

Max Act: 2.8888. Min Act: -0.0001

Data Index: 79599 (C4 (Web Text))

Max Activating Token Index: 37