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

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

Neuron 1220 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4783. Min Act: -0.0002

Data Index: 998682 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4121. Min Act: -0.0002

Data Index: 512315 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3898. Min Act: -0.0002

Data Index: 1243251 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3650. Min Act: -0.0002

Data Index: 973299 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4331. Min Act: -0.0002

Data Index: 358979 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4073. Min Act: -0.0002

Data Index: 1199261 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3716. Min Act: -0.0002

Data Index: 549891 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3376. Min Act: -0.0002

Data Index: 24591 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3860. Min Act: -0.0002

Data Index: 516759 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3771. Min Act: -0.0002

Data Index: 437933 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3907. Min Act: -0.0002

Data Index: 974238 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4024. Min Act: -0.0002

Data Index: 873037 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3978. Min Act: -0.0002

Data Index: 149475 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3676. Min Act: -0.0002

Data Index: 1211790 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3522. Min Act: -0.0002

Data Index: 1278604 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3410. Min Act: -0.0002

Data Index: 231346 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3407. Min Act: -0.0002

Data Index: 236945 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4095. Min Act: -0.0002

Data Index: 1130599 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3989. Min Act: -0.0002

Data Index: 783863 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3720. Min Act: -0.0002

Data Index: 464797 (C4 (Web Text))

Max Activating Token Index: 425