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

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

Neuron 1335 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: 2.9182. Min Range: -2.9182

Max Act: 2.9182. Min Act: -0.0000

Data Index: 70940 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.6659. Min Act: -0.0000

Data Index: 1328750 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.6616. Min Act: -0.0000

Data Index: 1286274 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2843. Min Act: -0.0000

Data Index: 1092525 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.5101. Min Act: -0.0000

Data Index: 1141226 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.4521. Min Act: -0.0000

Data Index: 259643 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.4083. Min Act: -0.0000

Data Index: 928906 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2377. Min Act: -0.0000

Data Index: 837833 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2286. Min Act: -0.0000

Data Index: 1240208 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.3119. Min Act: -0.0000

Data Index: 291252 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.1945. Min Act: -0.0000

Data Index: 613654 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2729. Min Act: -0.0000

Data Index: 1104531 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1122731 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2589. Min Act: -0.0000

Data Index: 1101917 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2283. Min Act: -0.0000

Data Index: 656797 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.2089. Min Act: -0.0000

Data Index: 1037463 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.0733. Min Act: -0.0000

Data Index: 791572 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.3183. Min Act: -0.0000

Data Index: 1009783 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.1926. Min Act: -0.0000

Data Index: 1339004 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 2.9182. Min Range: -2.9182

Max Act: 2.0652. Min Act: -0.0000

Data Index: 200788 (C4 (Web Text))

Max Activating Token Index: 356