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

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

Neuron 2252 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0665. Min Range: -3.0665

Max Act: 3.0665. Min Act: -0.0000

Data Index: 748993 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7346. Min Act: -0.0000

Data Index: 1148733 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.7119. Min Act: -0.0000

Data Index: 749551 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.6334. Min Act: -0.0000

Data Index: 70944 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.2752. Min Act: -0.0000

Data Index: 855344 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.2185. Min Act: -0.0000

Data Index: 619206 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.2210. Min Act: -0.0000

Data Index: 222719 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.2208. Min Act: -0.0000

Data Index: 646948 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.4205. Min Act: -0.0000

Data Index: 1148995 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.0293. Min Act: -0.0000

Data Index: 339355 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.1372. Min Act: 0.0000

Data Index: 187715 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.0405. Min Act: -0.0000

Data Index: 604615 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.1507. Min Act: -0.0000

Data Index: 38322 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 3.0665. Min Range: -3.0665

Max Act: 1.9990. Min Act: -0.0000

Data Index: 1016839 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 3.0665. Min Range: -3.0665

Max Act: 1.8611. Min Act: -0.0000

Data Index: 271482 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.0514. Min Act: -0.0000

Data Index: 902627 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.0665. Min Range: -3.0665

Max Act: 1.9036. Min Act: -0.0000

Data Index: 1057332 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 3.0665. Min Range: -3.0665

Max Act: 2.0259. Min Act: -0.0000

Data Index: 1145524 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 3.0665. Min Range: -3.0665

Max Act: 1.8781. Min Act: -0.0000

Data Index: 15437 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.0665. Min Range: -3.0665

Max Act: 1.8394. Min Act: -0.0000

Data Index: 978249 (C4 (Web Text))

Max Activating Token Index: 145