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

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

Neuron 97 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: 0.9155. Min Range: -0.9155

Max Act: 0.9155. Min Act: -0.0000

Data Index: 663207 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.8813. Min Act: -0.0000

Data Index: 395405 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1296064 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1027317 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7816. Min Act: -0.0000

Data Index: 259207 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.8075. Min Act: -0.0000

Data Index: 654849 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7909. Min Act: -0.0000

Data Index: 803791 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7582. Min Act: -0.0000

Data Index: 996262 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7807. Min Act: -0.0000

Data Index: 511162 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7487. Min Act: -0.0000

Data Index: 441041 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7633. Min Act: -0.0000

Data Index: 847275 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7304. Min Act: -0.0000

Data Index: 531157 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.7311. Min Act: -0.0000

Data Index: 87117 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1589218 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.6931. Min Act: -0.0000

Data Index: 834326 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1628583 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.6762. Min Act: -0.0000

Data Index: 664513 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.6902. Min Act: -0.0000

Data Index: 119038 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.6682. Min Act: -0.0000

Data Index: 552831 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.9155. Min Range: -0.9155

Max Act: 0.6632. Min Act: -0.0000

Data Index: 616638 (C4 (Web Text))

Max Activating Token Index: 817