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

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

Neuron 2536 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.4049. Min Act: -0.0000

Data Index: 653278 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1264126 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.0645. Min Act: -0.0000

Data Index: 56900 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.0295. Min Act: -0.0000

Data Index: 794052 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.0585. Min Act: -0.0000

Data Index: 410010 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1239613 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.0251. Min Act: -0.0000

Data Index: 905840 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9835. Min Act: -0.0000

Data Index: 274350 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9772. Min Act: -0.0000

Data Index: 1106037 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9703. Min Act: -0.0000

Data Index: 983498 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.0075. Min Act: -0.0000

Data Index: 728739 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1161708 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1359653 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1305929 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.4049. Min Range: -1.4049

Max Act: 1.0062. Min Act: -0.0000

Data Index: 262453 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.8869. Min Act: -0.0000

Data Index: 565135 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9016. Min Act: -0.0000

Data Index: 151697 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9318. Min Act: -0.0000

Data Index: 291994 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1049327 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.4049. Min Range: -1.4049

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1168770 (C4 (Web Text))

Max Activating Token Index: 269