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

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

Neuron 3628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1190. Min Act: -0.0001

Data Index: 974707 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1238868 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1117. Min Act: -0.0001

Data Index: 990969 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.1006. Min Act: -0.0000

Data Index: 835843 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0930. Min Act: -0.0000

Data Index: 667965 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1044563 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0874. Min Act: -0.0000

Data Index: 796867 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0832. Min Act: -0.0001

Data Index: 923797 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0873. Min Act: -0.0000

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1002231 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1200704 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0860. Min Act: -0.0000

Data Index: 778621 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0816. Min Act: -0.0000

Data Index: 586216 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0852. Min Act: -0.0001

Data Index: 831324 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1005198 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0813. Min Act: -0.0000

Data Index: 880667 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0835. Min Act: -0.0001

Data Index: 944627 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0799. Min Act: -0.0000

Data Index: 436722 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1148526 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.1190. Min Range: -0.1190

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1208150 (C4 (Web Text))

Max Activating Token Index: 774