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

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

Neuron 3587 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7107. Min Range: -2.7107

Max Act: 2.7107. Min Act: -0.0000

Data Index: 868392 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.8804. Min Act: -0.0000

Data Index: 20060 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.9530. Min Act: -0.0000

Data Index: 706054 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.8117. Min Act: -0.0000

Data Index: 425596 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.7107. Min Range: -2.7107

Max Act: 2.0375. Min Act: -0.0000

Data Index: 155061 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.8175. Min Act: -0.0000

Data Index: 1130356 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.6826. Min Act: -0.0000

Data Index: 1141181 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.8925. Min Act: -0.0000

Data Index: 1294730 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.7914. Min Act: -0.0000

Data Index: 932225 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.5763. Min Act: -0.0000

Data Index: 847337 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.7623. Min Act: -0.0000

Data Index: 197830 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1012334 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.8309. Min Act: -0.0000

Data Index: 1168806 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1240296 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.6931. Min Act: -0.0000

Data Index: 709043 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.6931. Min Act: -0.0000

Data Index: 1089142 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.5948. Min Act: -0.0000

Data Index: 883024 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.6812. Min Act: -0.0000

Data Index: 222766 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.5821. Min Act: -0.0000

Data Index: 735084 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 2.7107. Min Range: -2.7107

Max Act: 1.5751. Min Act: -0.0000

Data Index: 698059 (C4 (Web Text))

Max Activating Token Index: 611