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

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

Neuron 1339 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: 0.7481. Min Range: -0.7481

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1386260 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1630846 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1540733 (Python Code)

Max Activating Token Index: 98

Text #3

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1460383 (Python Code)

Max Activating Token Index: 257

Text #4

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1562962 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1599577 (Python Code)

Max Activating Token Index: 345

Text #6

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1365454 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1518496 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1559589 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1460231 (Python Code)

Max Activating Token Index: 665

Text #10

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5706. Min Act: -0.0000

Data Index: 1373307 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1380725 (Python Code)

Max Activating Token Index: 148

Text #12

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1452724 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1623062 (Python Code)

Max Activating Token Index: 366

Text #14

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1420148 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1360175 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1535404 (Python Code)

Max Activating Token Index: 344

Text #17

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1558406 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1364232 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 0.7481. Min Range: -0.7481

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1652200 (Python Code)

Max Activating Token Index: 509