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

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

Neuron 4659 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.9438. Min Act: -0.0000

Data Index: 509505 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 1.0539. Min Range: -1.0539

Max Act: 1.0539. Min Act: -0.0000

Data Index: 825408 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.7974. Min Act: -0.0000

Data Index: 750215 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.7291. Min Act: -0.0000

Data Index: 190177 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1220410 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6695. Min Act: -0.0000

Data Index: 514686 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6196. Min Act: -0.0000

Data Index: 600624 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1218838 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6279. Min Act: -0.0000

Data Index: 523071 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.5922. Min Act: -0.0000

Data Index: 399139 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1159589 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6039. Min Act: -0.0000

Data Index: 451653 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.5587. Min Act: -0.0000

Data Index: 642428 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.5783. Min Act: -0.0000

Data Index: 1315828 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.5546. Min Act: -0.0000

Data Index: 568620 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1303808 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6089. Min Act: -0.0000

Data Index: 818015 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.6163. Min Act: -0.0000

Data Index: 41983 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.5648. Min Act: -0.0000

Data Index: 486967 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.0539. Min Range: -1.0539

Max Act: 0.4987. Min Act: -0.0000

Data Index: 616703 (C4 (Web Text))

Max Activating Token Index: 116