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

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

Neuron 2011 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.8060. Min Act: -0.0001

Data Index: 417647 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7883. Min Act: -0.0001

Data Index: 162160 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7476. Min Act: -0.0001

Data Index: 173756 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7631. Min Act: -0.0001

Data Index: 962225 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7209. Min Act: -0.0001

Data Index: 139855 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7633. Min Act: -0.0001

Data Index: 436844 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7089. Min Act: -0.0001

Data Index: 336232 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7774. Min Act: -0.0001

Data Index: 810226 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7778. Min Act: -0.0001

Data Index: 271526 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7015. Min Act: -0.0001

Data Index: 140887 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7477. Min Act: -0.0001

Data Index: 820227 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7397. Min Act: -0.0001

Data Index: 595721 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.6797. Min Act: -0.0001

Data Index: 565052 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7162. Min Act: -0.0001

Data Index: 1351683 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7403. Min Act: -0.0001

Data Index: 926428 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7133. Min Act: -0.0001

Data Index: 431464 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.6885. Min Act: -0.0001

Data Index: 1129814 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.6613. Min Act: -0.0001

Data Index: 522698 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.6551. Min Act: -0.0001

Data Index: 946093 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.8060. Min Range: -0.8060

Max Act: 0.7609. Min Act: -0.0001

Data Index: 921478 (C4 (Web Text))

Max Activating Token Index: 758