Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 337 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0003

Data Index: 292711 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1362573 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1599391 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1421844 (Python Code)

Max Activating Token Index: 155

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0563. Min Act: -0.0003

Data Index: 56730 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1269991 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0598. Min Act: -0.0003

Data Index: 464516 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1525254 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1450408 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1535497 (Python Code)

Max Activating Token Index: 756

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1647246 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1043673 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0553. Min Act: -0.0003

Data Index: 839699 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1408609 (Python Code)

Max Activating Token Index: 799

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1466720 (Python Code)

Max Activating Token Index: 792

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0548. Min Act: -0.0003

Data Index: 548327 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1510950 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1394328 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1610417 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1426475 (Python Code)

Max Activating Token Index: 906