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

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

Neuron 500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1044190 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.2102. Min Act: -0.0000

Data Index: 690771 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.1665. Min Act: -0.0000

Data Index: 627677 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.1583. Min Act: -0.0000

Data Index: 156826 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.0855. Min Act: -0.0000

Data Index: 112541 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.0704. Min Act: -0.0000

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.0100. Min Act: -0.0000

Data Index: 348926 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9952. Min Act: -0.0000

Data Index: 249477 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1341989 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9372. Min Act: -0.0000

Data Index: 435496 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.2102. Min Range: -1.2102

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1206396 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1025185 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9015. Min Act: -0.0000

Data Index: 812532 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.9363. Min Act: -0.0000

Data Index: 130692 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8670. Min Act: -0.0000

Data Index: 482350 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8903. Min Act: -0.0000

Data Index: 660913 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8551. Min Act: -0.0000

Data Index: 103315 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8138. Min Act: -0.0000

Data Index: 964583 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1282305 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.2102. Min Range: -1.2102

Max Act: 0.7999. Min Act: -0.0000

Data Index: 1129594 (C4 (Web Text))

Max Activating Token Index: 807