Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6725. Min Act: -0.0001

Data Index: 511671 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6234. Min Act: -0.0001

Data Index: 349953 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.7034. Min Act: -0.0001

Data Index: 511934 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6316. Min Act: -0.0001

Data Index: 845635 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1133304 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5905. Min Act: -0.0001

Data Index: 1158595 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6554. Min Act: -0.0001

Data Index: 1086692 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5653. Min Act: -0.0001

Data Index: 1349576 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6169. Min Act: -0.0001

Data Index: 688786 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4936. Min Act: -0.0001

Data Index: 451674 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5457. Min Act: -0.0001

Data Index: 730862 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5386. Min Act: -0.0001

Data Index: 183326 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5521. Min Act: -0.0001

Data Index: 775734 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5255. Min Act: -0.0001

Data Index: 1335284 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5088. Min Act: -0.0001

Data Index: 189467 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4881. Min Act: -0.0001

Data Index: 710815 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6521. Min Act: -0.0001

Data Index: 430981 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5266. Min Act: -0.0001

Data Index: 1014988 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4969. Min Act: -0.0001

Data Index: 1267931 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1174079 (C4 (Web Text))

Max Activating Token Index: 563