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

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

Neuron 3273 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4837. Min Act: -0.0000

Data Index: 164909 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4688. Min Act: -0.0000

Data Index: 748232 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4628. Min Act: -0.0000

Data Index: 499849 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4533. Min Act: -0.0000

Data Index: 922435 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4273. Min Act: -0.0000

Data Index: 825722 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4123. Min Act: -0.0000

Data Index: 662167 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4444. Min Act: -0.0000

Data Index: 192747 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3754. Min Act: -0.0000

Data Index: 996215 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4120. Min Act: -0.0000

Data Index: 960526 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3716. Min Act: -0.0000

Data Index: 64674 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3975. Min Act: -0.0000

Data Index: 318205 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1038570 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3814. Min Act: -0.0000

Data Index: 737536 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3524. Min Act: -0.0000

Data Index: 189628 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3760. Min Act: -0.0000

Data Index: 190294 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3954. Min Act: -0.0000

Data Index: 494520 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1156331 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.4099. Min Act: -0.0000

Data Index: 538815 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1062162 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.4837. Min Range: -0.4837

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1196143 (C4 (Web Text))

Max Activating Token Index: 146