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

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

Neuron 5443 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3995. Min Range: -4.3995

Max Act: 4.3995. Min Act: -0.0000

Data Index: 605806 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 4.3995. Min Range: -4.3995

Max Act: 4.1405. Min Act: -0.0000

Data Index: 159420 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.9491. Min Act: -0.0000

Data Index: 63702 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.4820. Min Act: -0.0000

Data Index: 1002109 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.6429. Min Act: -0.0000

Data Index: 9015 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.5733. Min Act: -0.0000

Data Index: 205216 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.9198. Min Act: -0.0000

Data Index: 745665 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.5677. Min Act: -0.0000

Data Index: 454210 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.3203. Min Act: -0.0000

Data Index: 184349 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.6064. Min Act: -0.0000

Data Index: 1288321 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.7220. Min Act: -0.0000

Data Index: 1141915 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.5726. Min Act: -0.0000

Data Index: 741498 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.4283. Min Act: -0.0000

Data Index: 169676 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.2680. Min Act: -0.0000

Data Index: 1304566 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.3205. Min Act: -0.0000

Data Index: 333727 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.2709. Min Act: -0.0000

Data Index: 144535 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.4326. Min Act: -0.0000

Data Index: 711619 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.1647. Min Act: -0.0000

Data Index: 1007997 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.3724. Min Act: -0.0000

Data Index: 283162 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 4.3995. Min Range: -4.3995

Max Act: 3.0679. Min Act: -0.0000

Data Index: 483271 (C4 (Web Text))

Max Activating Token Index: 160