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

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

Neuron 5276 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: 1.4762. Min Range: -1.4762

Max Act: 1.4762. Min Act: 0.0000

Data Index: 94357 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.4762. Min Range: -1.4762

Max Act: 1.2795. Min Act: -0.0000

Data Index: 987746 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.4762. Min Range: -1.4762

Max Act: 1.1741. Min Act: 0.0000

Data Index: 147179 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 1.4762. Min Range: -1.4762

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1192889 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.4762. Min Range: -1.4762

Max Act: 1.1510. Min Act: -0.0000

Data Index: 877389 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 1.4762. Min Range: -1.4762

Max Act: 1.1966. Min Act: 0.0000

Data Index: 621663 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.4762. Min Range: -1.4762

Max Act: 1.0803. Min Act: -0.0000

Data Index: 617752 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.4762. Min Range: -1.4762

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1096137 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.8641. Min Act: 0.0000

Data Index: 417314 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.8512. Min Act: -0.0000

Data Index: 909323 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.7729. Min Act: -0.0000

Data Index: 674906 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.6876. Min Act: 0.0000

Data Index: 95653 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.7464. Min Act: 0.0000

Data Index: 25311 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.6852. Min Act: -0.0000

Data Index: 244999 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.6591. Min Act: 0.0000

Data Index: 244282 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.6457. Min Act: 0.0000

Data Index: 216790 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.6105. Min Act: -0.0000

Data Index: 919888 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.5707. Min Act: -0.0000

Data Index: 810748 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1000928 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 1.4762. Min Range: -1.4762

Max Act: 0.5165. Min Act: 0.0000

Data Index: 430005 (C4 (Web Text))

Max Activating Token Index: 64