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

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

Neuron 4502 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.5690. Min Act: -0.0000

Data Index: 1187799 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.2668. Min Act: -0.0000

Data Index: 1010533 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.3396. Min Act: -0.0000

Data Index: 557774 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.1009. Min Act: -0.0000

Data Index: 931985 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.1119. Min Act: -0.0000

Data Index: 272449 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.9508. Min Act: -0.0000

Data Index: 786208 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.8267. Min Act: -0.0000

Data Index: 1117802 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.8147. Min Act: -0.0000

Data Index: 1220470 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.8838. Min Act: -0.0000

Data Index: 570045 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.9622. Min Act: -0.0000

Data Index: 653340 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.7405. Min Act: -0.0000

Data Index: 926421 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1201843 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.7960. Min Act: -0.0000

Data Index: 1265940 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6883. Min Act: -0.0000

Data Index: 979612 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6885. Min Act: -0.0000

Data Index: 141524 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.7797. Min Act: -0.0000

Data Index: 903124 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6589. Min Act: -0.0000

Data Index: 601520 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.9267. Min Act: -0.0000

Data Index: 470945 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6386. Min Act: -0.0000

Data Index: 823322 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.7235. Min Act: -0.0000

Data Index: 761859 (C4 (Web Text))

Max Activating Token Index: 1005