Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 676 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9970. Min Act: -0.0001

Data Index: 1009702 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9835. Min Act: -0.0001

Data Index: 590006 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9853. Min Act: -0.0001

Data Index: 766225 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9144. Min Act: -0.0001

Data Index: 1093071 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9422. Min Act: -0.0001

Data Index: 415731 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9276. Min Act: -0.0001

Data Index: 310707 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.9609. Min Act: -0.0001

Data Index: 1046285 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8949. Min Act: -0.0001

Data Index: 1327491 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8905. Min Act: -0.0001

Data Index: 725659 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8209. Min Act: -0.0001

Data Index: 742715 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8489. Min Act: -0.0001

Data Index: 332507 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1008339 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8245. Min Act: -0.0001

Data Index: 1038858 (C4 (Web Text))

Max Activating Token Index: 753

Text #13

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8007. Min Act: -0.0001

Data Index: 214458 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7846. Min Act: -0.0001

Data Index: 680623 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1294367 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8015. Min Act: -0.0001

Data Index: 502529 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.8268. Min Act: -0.0001

Data Index: 796083 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7744. Min Act: -0.0001

Data Index: 223137 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.9970. Min Range: -0.9970

Max Act: 0.7991. Min Act: -0.0001

Data Index: 108152 (C4 (Web Text))

Max Activating Token Index: 968