Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 592 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1136. Min Act: -0.0002

Data Index: 746505 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1063. Min Act: -0.0002

Data Index: 359306 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1038. Min Act: -0.0002

Data Index: 731567 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0990. Min Act: -0.0002

Data Index: 155456 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0993. Min Act: -0.0002

Data Index: 730315 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0998. Min Act: -0.0002

Data Index: 770037 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0961. Min Act: -0.0002

Data Index: 855007 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0955. Min Act: -0.0002

Data Index: 72824 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1258 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0887. Min Act: -0.0002

Data Index: 175754 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1041668 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0893. Min Act: -0.0002

Data Index: 528300 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1199913 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1165159 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0852. Min Act: -0.0002

Data Index: 671614 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1090628 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0843. Min Act: -0.0002

Data Index: 35176 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0855. Min Act: -0.0002

Data Index: 847684 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0878. Min Act: -0.0002

Data Index: 542221 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1252475 (C4 (Web Text))

Max Activating Token Index: 370