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

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

Neuron 1279 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.9178. Min Act: -0.0000

Data Index: 399377 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.3032. Min Act: -0.0000

Data Index: 5753 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.2852. Min Act: -0.0000

Data Index: 1172667 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.0730. Min Act: -0.0000

Data Index: 484410 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.1083. Min Act: -0.0000

Data Index: 591925 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.0840. Min Act: -0.0000

Data Index: 398112 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.0696. Min Act: -0.0000

Data Index: 298925 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.0237. Min Act: -0.0000

Data Index: 968120 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.0192. Min Act: -0.0000

Data Index: 324314 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.9178. Min Range: -1.9178

Max Act: 1.0286. Min Act: -0.0000

Data Index: 1268201 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.9434. Min Act: -0.0000

Data Index: 385568 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.9336. Min Act: -0.0000

Data Index: 683148 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.8406. Min Act: -0.0000

Data Index: 950391 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.8949. Min Act: -0.0000

Data Index: 1232887 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.9292. Min Act: -0.0000

Data Index: 857949 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.8500. Min Act: -0.0000

Data Index: 174910 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.8725. Min Act: -0.0000

Data Index: 464274 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.8072. Min Act: -0.0000

Data Index: 642227 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.7936. Min Act: -0.0000

Data Index: 442668 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 1.9178. Min Range: -1.9178

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1022531 (C4 (Web Text))

Max Activating Token Index: 922