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

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

Neuron 3211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.3143. Min Act: -0.0000

Data Index: 1179610 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.4824. Min Act: -0.0000

Data Index: 1320287 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.3899. Min Act: -0.0000

Data Index: 801249 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.4117. Min Act: -0.0001

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.1695. Min Act: -0.0001

Data Index: 1057671 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.3498. Min Act: -0.0000

Data Index: 82097 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 6.4824. Min Range: -6.4824

Max Act: 5.9620. Min Act: -0.0001

Data Index: 1280860 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.1532. Min Act: -0.0001

Data Index: 1034523 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.3351. Min Act: -0.0001

Data Index: 1025160 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.1302. Min Act: -0.0000

Data Index: 342573 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.0615. Min Act: -0.0001

Data Index: 449246 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.0159. Min Act: -0.0001

Data Index: 615778 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 6.4824. Min Range: -6.4824

Max Act: 5.9988. Min Act: -0.0001

Data Index: 819173 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.0012. Min Act: -0.0001

Data Index: 291960 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.1526. Min Act: -0.0001

Data Index: 730186 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.1492. Min Act: -0.0001

Data Index: 794660 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.1391. Min Act: -0.0000

Data Index: 981665 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 6.4824. Min Range: -6.4824

Max Act: 5.9422. Min Act: -0.0001

Data Index: 15475 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 6.4824. Min Range: -6.4824

Max Act: 6.1187. Min Act: -0.0001

Data Index: 779561 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 6.4824. Min Range: -6.4824

Max Act: 5.9348. Min Act: -0.0001

Data Index: 710455 (C4 (Web Text))

Max Activating Token Index: 331