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

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

Neuron 1220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.1893. Min Act: -0.0000

Data Index: 323104 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.1893. Min Range: -1.1893

Max Act: 1.0065. Min Act: -0.0000

Data Index: 306746 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1349120 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.9819. Min Act: -0.0000

Data Index: 443901 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.8770. Min Act: -0.0000

Data Index: 692122 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.8444. Min Act: -0.0000

Data Index: 360045 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.8566. Min Act: -0.0000

Data Index: 4008 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1098500 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1099000 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.7035. Min Act: -0.0000

Data Index: 58266 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1163141 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6639. Min Act: -0.0000

Data Index: 52023 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6629. Min Act: -0.0000

Data Index: 494804 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6236. Min Act: -0.0000

Data Index: 343865 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6558. Min Act: -0.0000

Data Index: 761569 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6465. Min Act: -0.0000

Data Index: 210678 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1290253 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1311933 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6368. Min Act: -0.0000

Data Index: 117969 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.1893. Min Range: -1.1893

Max Act: 0.6103. Min Act: -0.0000

Data Index: 601175 (C4 (Web Text))

Max Activating Token Index: 198