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

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

Neuron 1395 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: 1.5161. Min Range: -1.5161

Max Act: 1.5161. Min Act: -0.0000

Data Index: 547786 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1109717 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0732. Min Act: -0.0000

Data Index: 834700 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0918. Min Act: -0.0000

Data Index: 454770 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0855. Min Act: -0.0000

Data Index: 730742 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0107. Min Act: -0.0000

Data Index: 179119 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.5161. Min Range: -1.5161

Max Act: 1.0294. Min Act: -0.0000

Data Index: 485745 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9768. Min Act: -0.0000

Data Index: 454901 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1097616 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9845. Min Act: -0.0000

Data Index: 443508 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9059. Min Act: -0.0001

Data Index: 12278 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9719. Min Act: -0.0000

Data Index: 971386 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1275670 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9314. Min Act: -0.0000

Data Index: 550707 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9566. Min Act: -0.0000

Data Index: 907947 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8896. Min Act: -0.0000

Data Index: 224985 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8845. Min Act: -0.0000

Data Index: 40962 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9724. Min Act: -0.0000

Data Index: 407060 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.8786. Min Act: -0.0000

Data Index: 419875 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 1.5161. Min Range: -1.5161

Max Act: 0.9202. Min Act: -0.0000

Data Index: 567401 (C4 (Web Text))

Max Activating Token Index: 530