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

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

Neuron 2872 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6831. Min Act: -0.0000

Data Index: 948664 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5303. Min Act: -0.0000

Data Index: 670132 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4287. Min Act: -0.0000

Data Index: 282588 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5510. Min Act: -0.0000

Data Index: 679012 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4663. Min Act: -0.0000

Data Index: 323418 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5014. Min Act: -0.0000

Data Index: 922383 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4810. Min Act: -0.0000

Data Index: 656879 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4617. Min Act: -0.0000

Data Index: 566789 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4596. Min Act: -0.0000

Data Index: 923070 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4738. Min Act: -0.0000

Data Index: 421713 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1269056 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4585. Min Act: -0.0000

Data Index: 708050 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4742. Min Act: -0.0000

Data Index: 248997 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4376. Min Act: -0.0000

Data Index: 504186 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4231. Min Act: -0.0000

Data Index: 884611 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4521. Min Act: -0.0000

Data Index: 344668 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4325. Min Act: -0.0000

Data Index: 168470 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1137267 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4277. Min Act: -0.0000

Data Index: 386731 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4756. Min Act: -0.0000

Data Index: 546930 (C4 (Web Text))

Max Activating Token Index: 830