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

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

Neuron 2237 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: 0.9111. Min Range: -0.9111

Max Act: 0.9111. Min Act: -0.0000

Data Index: 584613 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8683. Min Act: -0.0000

Data Index: 374196 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7910. Min Act: -0.0000

Data Index: 544253 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.8207. Min Act: -0.0000

Data Index: 757856 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7950. Min Act: -0.0000

Data Index: 443743 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7898. Min Act: -0.0000

Data Index: 352338 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1194681 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7454. Min Act: -0.0000

Data Index: 384488 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7450. Min Act: -0.0000

Data Index: 884848 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7128. Min Act: -0.0000

Data Index: 998314 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7264. Min Act: -0.0000

Data Index: 250835 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6805. Min Act: -0.0000

Data Index: 122754 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7115. Min Act: -0.0000

Data Index: 822106 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6717. Min Act: -0.0000

Data Index: 791314 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7182. Min Act: -0.0000

Data Index: 947471 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7157. Min Act: -0.0000

Data Index: 198336 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1272656 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6968. Min Act: -0.0000

Data Index: 591746 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.7092. Min Act: -0.0000

Data Index: 934630 (C4 (Web Text))

Max Activating Token Index: 830

Text #19

Max Range: 0.9111. Min Range: -0.9111

Max Act: 0.6864. Min Act: -0.0000

Data Index: 465659 (C4 (Web Text))

Max Activating Token Index: 251