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

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

Neuron 3510 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.8196. Min Act: -0.0000

Data Index: 505355 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.3164. Min Act: -0.0000

Data Index: 1139337 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.0509. Min Act: -0.0000

Data Index: 528156 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.3416. Min Act: -0.0000

Data Index: 19152 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.0893. Min Act: -0.0000

Data Index: 1111903 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.0556. Min Act: -0.0000

Data Index: 589943 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.8906. Min Act: -0.0000

Data Index: 180048 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.0551. Min Act: -0.0000

Data Index: 835292 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9160. Min Act: -0.0000

Data Index: 103107 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.8196. Min Range: -2.8196

Max Act: 2.0225. Min Act: -0.0000

Data Index: 1039496 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9591. Min Act: -0.0000

Data Index: 764364 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9453. Min Act: -0.0000

Data Index: 73150 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9178. Min Act: -0.0000

Data Index: 859597 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1058190 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7930. Min Act: -0.0000

Data Index: 421274 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1326399 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.7193. Min Act: -0.0000

Data Index: 862515 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.8063. Min Act: -0.0000

Data Index: 361108 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.9135. Min Act: -0.0000

Data Index: 907544 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 2.8196. Min Range: -2.8196

Max Act: 1.8593. Min Act: -0.0000

Data Index: 275536 (C4 (Web Text))

Max Activating Token Index: 675