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

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

Neuron 2050 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: 3.5819. Min Range: -3.5819

Max Act: 3.5819. Min Act: -0.0000

Data Index: 1318620 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 3.5819. Min Range: -3.5819

Max Act: 3.2335. Min Act: -0.0000

Data Index: 245238 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 3.5819. Min Range: -3.5819

Max Act: 3.0903. Min Act: -0.0000

Data Index: 337398 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.6595. Min Act: -0.0000

Data Index: 1282366 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.2103. Min Act: -0.0000

Data Index: 1160532 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 3.5819. Min Range: -3.5819

Max Act: 2.0977. Min Act: -0.0000

Data Index: 399447 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.9548. Min Act: -0.0000

Data Index: 643723 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.9121. Min Act: -0.0000

Data Index: 115172 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.8802. Min Act: -0.0000

Data Index: 594994 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.8512. Min Act: -0.0000

Data Index: 734796 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.8923. Min Act: -0.0000

Data Index: 824341 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.7718. Min Act: -0.0000

Data Index: 223028 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.7586. Min Act: -0.0000

Data Index: 427646 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.6616. Min Act: -0.0000

Data Index: 596006 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.6605. Min Act: -0.0000

Data Index: 1229057 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.7496. Min Act: -0.0000

Data Index: 593626 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.7381. Min Act: -0.0000

Data Index: 730668 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.7249. Min Act: -0.0000

Data Index: 854332 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.7052. Min Act: -0.0000

Data Index: 894727 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 3.5819. Min Range: -3.5819

Max Act: 1.7410. Min Act: -0.0000

Data Index: 660300 (C4 (Web Text))

Max Activating Token Index: 472