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

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

Neuron 1144 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: 0.4769. Min Range: -0.4769

Max Act: 0.4769. Min Act: -0.0000

Data Index: 280612 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1099177 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3744. Min Act: -0.0000

Data Index: 142239 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3989. Min Act: -0.0000

Data Index: 102526 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3500. Min Act: -0.0000

Data Index: 259436 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3424. Min Act: -0.0000

Data Index: 679123 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3244. Min Act: -0.0000

Data Index: 106861 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3144. Min Act: -0.0000

Data Index: 105774 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3317. Min Act: -0.0000

Data Index: 394617 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2814. Min Act: -0.0000

Data Index: 406128 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3154. Min Act: -0.0000

Data Index: 132002 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3139. Min Act: -0.0000

Data Index: 934456 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2936. Min Act: 0.0000

Data Index: 245560 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.3191. Min Act: -0.0000

Data Index: 235416 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1400934 (Python Code)

Max Activating Token Index: 977

Text #15

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2986. Min Act: -0.0000

Data Index: 890184 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2707. Min Act: -0.0000

Data Index: 956517 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2805. Min Act: -0.0000

Data Index: 678131 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1058302 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.4769. Min Range: -0.4769

Max Act: 0.2859. Min Act: -0.0000

Data Index: 34448 (C4 (Web Text))

Max Activating Token Index: 312