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

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

Neuron 1814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6997. Min Act: -0.0000

Data Index: 924971 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1222719 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.7919. Min Act: -0.0000

Data Index: 139385 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1211607 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.7603. Min Act: -0.0000

Data Index: 29300 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1346545 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6903. Min Act: -0.0000

Data Index: 962099 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6685. Min Act: -0.0000

Data Index: 691046 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1324285 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1352378 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1477240 (Python Code)

Max Activating Token Index: 744

Text #11

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6397. Min Act: -0.0000

Data Index: 234991 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.5858. Min Act: -0.0000

Data Index: 490435 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6313. Min Act: -0.0000

Data Index: 129008 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6014. Min Act: -0.0000

Data Index: 701438 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6049. Min Act: -0.0000

Data Index: 627640 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6052. Min Act: -0.0000

Data Index: 967502 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6091. Min Act: -0.0000

Data Index: 700076 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.6024. Min Act: -0.0000

Data Index: 441248 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.8552. Min Range: -0.8552

Max Act: 0.5606. Min Act: -0.0000

Data Index: 680324 (C4 (Web Text))

Max Activating Token Index: 947