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

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

Neuron 4561 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: 0.6259. Min Range: -0.6259

Max Act: 0.6130. Min Act: -0.0000

Data Index: 757715 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.6259. Min Act: -0.0000

Data Index: 605392 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5945. Min Act: -0.0000

Data Index: 976869 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5862. Min Act: -0.0000

Data Index: 704914 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5851. Min Act: -0.0000

Data Index: 250743 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5099. Min Act: -0.0000

Data Index: 853872 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5601. Min Act: -0.0000

Data Index: 162720 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5317. Min Act: -0.0000

Data Index: 75360 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5363. Min Act: -0.0000

Data Index: 949162 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.5233. Min Act: -0.0000

Data Index: 706378 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4550. Min Act: -0.0000

Data Index: 195714 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4687. Min Act: -0.0000

Data Index: 218320 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4681. Min Act: -0.0000

Data Index: 494840 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4808. Min Act: -0.0000

Data Index: 679132 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4629. Min Act: -0.0000

Data Index: 369755 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4919. Min Act: -0.0000

Data Index: 647189 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4565. Min Act: -0.0000

Data Index: 548157 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4684. Min Act: -0.0000

Data Index: 628283 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4149. Min Act: -0.0000

Data Index: 687751 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.6259. Min Range: -0.6259

Max Act: 0.4459. Min Act: -0.0000

Data Index: 397307 (C4 (Web Text))

Max Activating Token Index: 798