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

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

Neuron 1854 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1241914 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.8232. Min Act: 0.0001

Data Index: 952550 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7858. Min Act: -0.0000

Data Index: 240816 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1193916 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7448. Min Act: -0.0000

Data Index: 88337 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7646. Min Act: 0.0001

Data Index: 523168 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7785. Min Act: -0.0000

Data Index: 920019 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1268075 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7556. Min Act: -0.0000

Data Index: 969178 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1115701 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7585. Min Act: 0.0001

Data Index: 757415 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7352. Min Act: 0.0000

Data Index: 562446 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7014. Min Act: -0.0000

Data Index: 725205 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7183. Min Act: -0.0000

Data Index: 298001 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7374. Min Act: -0.0000

Data Index: 407489 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7081. Min Act: -0.0000

Data Index: 154262 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7021. Min Act: 0.0001

Data Index: 872255 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6829. Min Act: -0.0000

Data Index: 605771 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7216. Min Act: -0.0000

Data Index: 797220 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7012. Min Act: -0.0000

Data Index: 519534 (C4 (Web Text))

Max Activating Token Index: 816