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

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

Neuron 4241 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.7682. Min Act: -0.0000

Data Index: 16644 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.7836. Min Act: -0.0000

Data Index: 323108 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1286362 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6755. Min Act: -0.0000

Data Index: 825654 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.7690. Min Act: -0.0000

Data Index: 415649 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6878. Min Act: -0.0000

Data Index: 1223880 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6776. Min Act: -0.0000

Data Index: 762208 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1047625 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1176043 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1177387 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6513. Min Act: -0.0000

Data Index: 513818 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6109. Min Act: -0.0000

Data Index: 341244 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6344. Min Act: -0.0000

Data Index: 268136 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6723. Min Act: -0.0000

Data Index: 827762 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1330840 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1042506 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5546. Min Act: -0.0000

Data Index: 478942 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1076951 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.5477. Min Act: -0.0000

Data Index: 76234 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.7836. Min Range: -0.7836

Max Act: 0.6032. Min Act: -0.0000

Data Index: 675857 (C4 (Web Text))

Max Activating Token Index: 870