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

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

Neuron 647 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: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0000

Data Index: 238449 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1222642 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1010516 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0936. Min Act: -0.0000

Data Index: 729206 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0925. Min Act: -0.0000

Data Index: 799056 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0987. Min Act: -0.0000

Data Index: 924801 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0870. Min Act: -0.0000

Data Index: 194602 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1039652 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1311613 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0831. Min Act: -0.0000

Data Index: 225786 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0841. Min Act: -0.0000

Data Index: 775615 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0831. Min Act: -0.0000

Data Index: 642365 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0821. Min Act: -0.0000

Data Index: 492418 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0868. Min Act: -0.0000

Data Index: 601433 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1114932 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1315910 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0770. Min Act: -0.0000

Data Index: 849616 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0801. Min Act: -0.0000

Data Index: 469155 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0792. Min Act: -0.0000

Data Index: 445513 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0817. Min Act: -0.0000

Data Index: 855152 (C4 (Web Text))

Max Activating Token Index: 338