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

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

Neuron 4127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.5966. Min Act: -0.0000

Data Index: 122844 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 2.5966. Min Range: -2.5966

Max Act: 2.1149. Min Act: -0.0000

Data Index: 992828 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1105538 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.4009. Min Act: -0.0000

Data Index: 370624 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1264239 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.2468. Min Act: -0.0000

Data Index: 706525 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.2719. Min Act: -0.0000

Data Index: 197852 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1094436 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.1792. Min Act: -0.0000

Data Index: 994818 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.2319. Min Act: -0.0000

Data Index: 1232973 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.1720. Min Act: -0.0000

Data Index: 515992 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.2202. Min Act: -0.0000

Data Index: 22930 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1169111 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.1397. Min Act: -0.0000

Data Index: 1235991 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.0774. Min Act: -0.0000

Data Index: 350591 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.2558. Min Act: -0.0000

Data Index: 655310 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 2.5966. Min Range: -2.5966

Max Act: 0.9538. Min Act: -0.0000

Data Index: 154241 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1099423 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.1019. Min Act: -0.0000

Data Index: 930561 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 2.5966. Min Range: -2.5966

Max Act: 1.0908. Min Act: -0.0000

Data Index: 377868 (C4 (Web Text))

Max Activating Token Index: 171