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

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

Neuron 1230 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: 4.4836. Min Range: -4.4836

Max Act: 4.4836. Min Act: -0.0000

Data Index: 341699 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 4.4836. Min Range: -4.4836

Max Act: 4.0815. Min Act: -0.0000

Data Index: 1237496 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.9612. Min Act: -0.0000

Data Index: 660688 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.6923. Min Act: -0.0000

Data Index: 340335 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.3065. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.2522. Min Act: -0.0000

Data Index: 255864 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.1775. Min Act: -0.0000

Data Index: 119936 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.9442. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.2369. Min Act: -0.0000

Data Index: 90553 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.2303. Min Act: -0.0000

Data Index: 62963 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.9811. Min Act: -0.0000

Data Index: 193930 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.9846. Min Act: -0.0000

Data Index: 293014 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.9113. Min Act: -0.0000

Data Index: 1067818 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.8842. Min Act: -0.0000

Data Index: 385695 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.7374. Min Act: -0.0000

Data Index: 975054 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 4.4836. Min Range: -4.4836

Max Act: 3.0109. Min Act: -0.0000

Data Index: 678132 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.8341. Min Act: -0.0000

Data Index: 280880 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.6693. Min Act: -0.0000

Data Index: 184091 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.8109. Min Act: -0.0000

Data Index: 1245449 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 4.4836. Min Range: -4.4836

Max Act: 2.7865. Min Act: -0.0000

Data Index: 673462 (C4 (Web Text))

Max Activating Token Index: 486