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

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

Neuron 2139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6544. Min Range: -5.6544

Max Act: 5.4464. Min Act: -0.0000

Data Index: 633199 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 5.6544. Min Range: -5.6544

Max Act: 5.6544. Min Act: -0.0000

Data Index: 1193824 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 5.6544. Min Range: -5.6544

Max Act: 5.5536. Min Act: -0.0000

Data Index: 632816 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.1029. Min Act: -0.0000

Data Index: 95973 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.6089. Min Act: -0.0000

Data Index: 82750 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.3890. Min Act: -0.0000

Data Index: 397075 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.4926. Min Act: -0.0000

Data Index: 418682 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.4975. Min Act: -0.0000

Data Index: 590354 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.1727. Min Act: -0.0000

Data Index: 417936 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.3261. Min Act: -0.0000

Data Index: 1188428 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.2661. Min Act: -0.0000

Data Index: 594234 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.1930. Min Act: -0.0000

Data Index: 153926 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.1713. Min Act: -0.0000

Data Index: 1022265 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.1472. Min Act: -0.0000

Data Index: 1126361 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.3138. Min Act: -0.0000

Data Index: 140306 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.2711. Min Act: -0.0000

Data Index: 635893 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.2611. Min Act: -0.0000

Data Index: 1175351 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.2504. Min Act: -0.0000

Data Index: 1038167 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 5.6544. Min Range: -5.6544

Max Act: 4.3686. Min Act: -0.0000

Data Index: 1357533 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 5.6544. Min Range: -5.6544

Max Act: 3.8067. Min Act: -0.0000

Data Index: 1233599 (C4 (Web Text))

Max Activating Token Index: 820