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

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

Neuron 1065 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: 0.9860. Min Range: -0.9860

Max Act: 0.9860. Min Act: -0.0000

Data Index: 126138 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.9029. Min Act: -0.0000

Data Index: 514029 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1173394 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8401. Min Act: -0.0000

Data Index: 474799 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8523. Min Act: -0.0000

Data Index: 833282 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8201. Min Act: -0.0000

Data Index: 535655 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8069. Min Act: -0.0000

Data Index: 988904 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8241. Min Act: -0.0000

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8248. Min Act: -0.0000

Data Index: 176640 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8545. Min Act: -0.0000

Data Index: 353953 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7939. Min Act: -0.0000

Data Index: 478647 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8109. Min Act: -0.0000

Data Index: 331425 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8070. Min Act: -0.0000

Data Index: 413072 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1350279 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7687. Min Act: -0.0000

Data Index: 544968 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7614. Min Act: -0.0000

Data Index: 593507 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.8175. Min Act: -0.0000

Data Index: 890640 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7871. Min Act: -0.0000

Data Index: 468535 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7539. Min Act: -0.0000

Data Index: 32293 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.9860. Min Range: -0.9860

Max Act: 0.7786. Min Act: -0.0000

Data Index: 956851 (C4 (Web Text))

Max Activating Token Index: 146