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

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

Neuron 4543 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: 2.1398. Min Range: -2.1398

Max Act: 2.1398. Min Act: -0.0000

Data Index: 457512 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 2.1398. Min Range: -2.1398

Max Act: 2.1277. Min Act: -0.0000

Data Index: 657177 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8069. Min Act: -0.0000

Data Index: 1314829 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.9152. Min Act: -0.0000

Data Index: 448770 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8742. Min Act: -0.0000

Data Index: 571223 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8640. Min Act: -0.0000

Data Index: 508582 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.7453. Min Act: -0.0000

Data Index: 1214298 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.7523. Min Act: 0.0000

Data Index: 590785 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8479. Min Act: -0.0000

Data Index: 1010735 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.7182. Min Act: -0.0000

Data Index: 18139 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.5622. Min Act: -0.0000

Data Index: 140489 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.6663. Min Act: -0.0000

Data Index: 1167943 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.6528. Min Act: -0.0000

Data Index: 147678 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.6420. Min Act: -0.0000

Data Index: 462773 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.6504. Min Act: -0.0000

Data Index: 1102038 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.8299. Min Act: -0.0000

Data Index: 944892 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.5340. Min Act: -0.0000

Data Index: 485145 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.5408. Min Act: -0.0000

Data Index: 767791 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.6115. Min Act: -0.0000

Data Index: 1056281 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 2.1398. Min Range: -2.1398

Max Act: 1.6126. Min Act: -0.0000

Data Index: 217225 (C4 (Web Text))

Max Activating Token Index: 1020