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

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

Neuron 3380 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0919. Min Range: -1.0919

Max Act: 1.0919. Min Act: -0.0000

Data Index: 841565 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.0919. Min Range: -1.0919

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1255242 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.8639. Min Act: -0.0000

Data Index: 5583 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1251910 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.7839. Min Act: -0.0000

Data Index: 738937 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.7609. Min Act: -0.0000

Data Index: 450923 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.7430. Min Act: -0.0000

Data Index: 114104 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.7171. Min Act: -0.0000

Data Index: 343773 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1070899 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6765. Min Act: -0.0000

Data Index: 7977 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6938. Min Act: -0.0000

Data Index: 901538 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6678. Min Act: -0.0000

Data Index: 679680 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6700. Min Act: -0.0000

Data Index: 79150 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1145774 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6822. Min Act: -0.0000

Data Index: 30806 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6965. Min Act: -0.0000

Data Index: 772302 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6504. Min Act: -0.0000

Data Index: 628010 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1060716 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1308579 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 1.0919. Min Range: -1.0919

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1088106 (C4 (Web Text))

Max Activating Token Index: 776