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

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

Neuron 90 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.1619. Min Act: -0.0003

Data Index: 154686 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.1619. Min Range: -1.1619

Max Act: 1.0006. Min Act: -0.0002

Data Index: 1008064 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9612. Min Act: -0.0002

Data Index: 894339 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9478. Min Act: -0.0002

Data Index: 45075 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9653. Min Act: -0.0002

Data Index: 1638221 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9628. Min Act: -0.0002

Data Index: 1115425 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9297. Min Act: -0.0003

Data Index: 959452 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9400. Min Act: -0.0002

Data Index: 1109155 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9280. Min Act: -0.0003

Data Index: 469031 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9438. Min Act: -0.0002

Data Index: 1174404 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9236. Min Act: -0.0002

Data Index: 367667 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9368. Min Act: -0.0002

Data Index: 31808 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9259. Min Act: -0.0003

Data Index: 805536 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9011. Min Act: -0.0002

Data Index: 1166750 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9080. Min Act: -0.0002

Data Index: 322322 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9052. Min Act: -0.0002

Data Index: 1001810 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8971. Min Act: -0.0002

Data Index: 1247729 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8922. Min Act: -0.0002

Data Index: 930138 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.9067. Min Act: -0.0002

Data Index: 999894 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.1619. Min Range: -1.1619

Max Act: 0.8788. Min Act: -0.0002

Data Index: 1109918 (C4 (Web Text))

Max Activating Token Index: 674