Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.9060. Min Act: -0.0001

Data Index: 110443 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8991. Min Act: -0.0001

Data Index: 912766 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8470. Min Act: -0.0001

Data Index: 316414 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8298. Min Act: -0.0000

Data Index: 887475 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1210369 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1254973 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8060. Min Act: -0.0000

Data Index: 548798 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7598. Min Act: -0.0000

Data Index: 29970 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7919. Min Act: -0.0000

Data Index: 725008 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7852. Min Act: -0.0000

Data Index: 475310 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1017599 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7791. Min Act: -0.0000

Data Index: 872277 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7467. Min Act: -0.0001

Data Index: 300195 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1115653 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7611. Min Act: -0.0000

Data Index: 797711 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7298. Min Act: -0.0000

Data Index: 427050 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1100276 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.7439. Min Act: -0.0000

Data Index: 355627 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6952. Min Act: -0.0001

Data Index: 449308 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.9060. Min Range: -0.9060

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1328893 (C4 (Web Text))

Max Activating Token Index: 151