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

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

Neuron 857 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9906. Min Act: -0.0001

Data Index: 98983 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 4.0652. Min Range: -4.0652

Max Act: 4.0652. Min Act: -0.0000

Data Index: 971341 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 4.0652. Min Range: -4.0652

Max Act: 4.0343. Min Act: -0.0001

Data Index: 1189055 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.4582. Min Act: -0.0001

Data Index: 950065 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.1062. Min Act: -0.0000

Data Index: 334534 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.4736. Min Act: -0.0001

Data Index: 943837 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.5798. Min Act: -0.0001

Data Index: 1197114 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.5115. Min Act: -0.0001

Data Index: 1286343 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.1248. Min Act: -0.0001

Data Index: 449635 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.4255. Min Act: -0.0001

Data Index: 912991 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.1911. Min Act: -0.0001

Data Index: 1243560 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.3273. Min Act: -0.0001

Data Index: 1038646 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.0648. Min Act: -0.0001

Data Index: 159104 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 4.0652. Min Range: -4.0652

Max Act: 2.9693. Min Act: -0.0001

Data Index: 852292 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.1073. Min Act: -0.0001

Data Index: 549386 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.0722. Min Act: -0.0001

Data Index: 959652 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.0382. Min Act: -0.0001

Data Index: 1085247 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.1374. Min Act: -0.0001

Data Index: 640479 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 4.0652. Min Range: -4.0652

Max Act: 2.6898. Min Act: -0.0001

Data Index: 122708 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.1439. Min Act: -0.0001

Data Index: 429557 (C4 (Web Text))

Max Activating Token Index: 357