Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1775 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8198. Min Act: -0.0001

Data Index: 1187295 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7639. Min Act: -0.0001

Data Index: 1561053 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8108. Min Act: -0.0001

Data Index: 1435567 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7973. Min Act: -0.0001

Data Index: 1479073 (Python Code)

Max Activating Token Index: 330

Text #4

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7201. Min Act: -0.0001

Data Index: 558150 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8233. Min Act: -0.0001

Data Index: 1416214 (Python Code)

Max Activating Token Index: 323

Text #6

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7557. Min Act: -0.0001

Data Index: 1510315 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1643561 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8026. Min Act: -0.0001

Data Index: 1553526 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7800. Min Act: -0.0001

Data Index: 1635663 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1384123 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1597703 (Python Code)

Max Activating Token Index: 357

Text #12

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7541. Min Act: -0.0001

Data Index: 317614 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7207. Min Act: -0.0001

Data Index: 1430332 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7864. Min Act: -0.0001

Data Index: 1460443 (Python Code)

Max Activating Token Index: 86

Text #15

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1601463 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7614. Min Act: -0.0001

Data Index: 1638337 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1391567 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7399. Min Act: -0.0001

Data Index: 1610597 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 0.8233. Min Range: -0.8233

Max Act: 0.7401. Min Act: -0.0001

Data Index: 1377880 (Python Code)

Max Activating Token Index: 887