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

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

Neuron 3807 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0002

Data Index: 832464 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1286159 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0567. Min Act: -0.0002

Data Index: 597565 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0537. Min Act: -0.0002

Data Index: 646033 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1593870 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1488090 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1051992 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1538084 (Python Code)

Max Activating Token Index: 529

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0506. Min Act: -0.0002

Data Index: 934717 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1565954 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1457762 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1381098 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1554884 (Python Code)

Max Activating Token Index: 424

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1452750 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1541173 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1617590 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1561980 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1474434 (Python Code)

Max Activating Token Index: 30

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1627876 (Python Code)

Max Activating Token Index: 160

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1604244 (Python Code)

Max Activating Token Index: 708