Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4456 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1032. Min Range: -1.1032

Max Act: 1.0982. Min Act: -0.0000

Data Index: 352686 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 1.1032. Min Range: -1.1032

Max Act: 1.1032. Min Act: -0.0000

Data Index: 210430 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8959. Min Act: -0.0000

Data Index: 600483 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8509. Min Act: 0.0000

Data Index: 645503 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8925. Min Act: 0.0000

Data Index: 223542 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.9210. Min Act: -0.0000

Data Index: 670506 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8491. Min Act: -0.0000

Data Index: 521497 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8674. Min Act: -0.0000

Data Index: 727941 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8868. Min Act: -0.0000

Data Index: 597530 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1102949 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8401. Min Act: -0.0000

Data Index: 863070 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8747. Min Act: -0.0000

Data Index: 373843 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1053646 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7895. Min Act: -0.0000

Data Index: 84519 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1210993 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7613. Min Act: 0.0000

Data Index: 493544 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7656. Min Act: -0.0000

Data Index: 547764 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7446. Min Act: -0.0000

Data Index: 168217 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7789. Min Act: -0.0000

Data Index: 486802 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1359230 (C4 (Web Text))

Max Activating Token Index: 739