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

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

Neuron 2580 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: 1.0880. Min Range: -1.0880

Max Act: 1.0880. Min Act: -0.0000

Data Index: 866619 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0386. Min Act: -0.0000

Data Index: 535281 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9389. Min Act: -0.0000

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9549. Min Act: -0.0000

Data Index: 398388 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0057. Min Act: -0.0000

Data Index: 922897 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9957. Min Act: -0.0000

Data Index: 747448 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9219. Min Act: -0.0000

Data Index: 783557 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9113. Min Act: -0.0000

Data Index: 478749 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1228621 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8663. Min Act: -0.0000

Data Index: 766703 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9251. Min Act: -0.0000

Data Index: 484085 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8803. Min Act: -0.0000

Data Index: 330342 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1316622 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.0880. Min Range: -1.0880

Max Act: 1.0063. Min Act: -0.0000

Data Index: 409782 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8156. Min Act: -0.0000

Data Index: 305805 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8391. Min Act: -0.0000

Data Index: 713424 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8594. Min Act: -0.0000

Data Index: 729816 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1082181 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1345029 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.0880. Min Range: -1.0880

Max Act: 0.8246. Min Act: -0.0000

Data Index: 956446 (C4 (Web Text))

Max Activating Token Index: 930