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

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

Neuron 654 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: 1.0836. Min Range: -1.0836

Max Act: 1.0193. Min Act: -0.0000

Data Index: 1328363 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0091. Min Act: -0.0000

Data Index: 160842 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0836. Min Act: -0.0000

Data Index: 197583 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1246343 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9685. Min Act: -0.0000

Data Index: 51436 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9339. Min Act: -0.0000

Data Index: 951764 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9584. Min Act: -0.0000

Data Index: 691746 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9339. Min Act: -0.0000

Data Index: 383182 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1043068 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9318. Min Act: -0.0000

Data Index: 429990 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9021. Min Act: -0.0000

Data Index: 987976 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8948. Min Act: -0.0000

Data Index: 747137 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1098012 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9270. Min Act: -0.0000

Data Index: 133268 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8910. Min Act: -0.0000

Data Index: 920231 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8923. Min Act: -0.0000

Data Index: 910244 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8401. Min Act: -0.0000

Data Index: 803330 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8489. Min Act: -0.0000

Data Index: 708131 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8732. Min Act: -0.0000

Data Index: 896784 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1309889 (C4 (Web Text))

Max Activating Token Index: 512