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

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

Neuron 2446 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.6257. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.2262. Min Act: -0.0000

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.2752. Min Act: -0.0000

Data Index: 1099799 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.1504. Min Act: -0.0000

Data Index: 183654 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.2509. Min Act: -0.0000

Data Index: 625219 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.1789. Min Act: -0.0000

Data Index: 141538 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0132. Min Act: -0.0000

Data Index: 754454 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0926. Min Act: -0.0000

Data Index: 728975 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.1121. Min Act: -0.0000

Data Index: 457554 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0649. Min Act: -0.0000

Data Index: 944924 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0746. Min Act: -0.0000

Data Index: 338517 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1267997 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1048201 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0292. Min Act: -0.0000

Data Index: 247865 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.6257. Min Range: -1.6257

Max Act: 0.9835. Min Act: -0.0000

Data Index: 924623 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1208189 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.6257. Min Range: -1.6257

Max Act: 0.9485. Min Act: -0.0000

Data Index: 1580984 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 1.6257. Min Range: -1.6257

Max Act: 0.9471. Min Act: -0.0000

Data Index: 182040 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.6257. Min Range: -1.6257

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1580692 (Python Code)

Max Activating Token Index: 941