Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 517 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.8371. Min Act: -0.0000

Data Index: 787554 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1313730 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.6201. Min Act: 0.0000

Data Index: 989610 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.5372. Min Act: -0.0000

Data Index: 565863 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.5650. Min Act: -0.0000

Data Index: 774028 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1473746 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.5686. Min Act: -0.0000

Data Index: 789431 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1075677 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4729. Min Act: 0.0000

Data Index: 108534 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4416. Min Act: -0.0000

Data Index: 150567 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4874. Min Act: -0.0000

Data Index: 320850 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4699. Min Act: 0.0000

Data Index: 255056 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1327700 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1363775 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1081373 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4103. Min Act: -0.0000

Data Index: 173020 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.3895. Min Act: -0.0000

Data Index: 723074 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1220013 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.3898. Min Act: -0.0000

Data Index: 74503 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.8371. Min Range: -0.8371

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1456640 (Python Code)

Max Activating Token Index: 64