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

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

Neuron 3790 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: 1.0802. Min Range: -1.0802

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1586785 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9751. Min Act: -0.0000

Data Index: 146550 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1372194 (Python Code)

Max Activating Token Index: 762

Text #3

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0414. Min Act: -0.0000

Data Index: 107031 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1420537 (Python Code)

Max Activating Token Index: 426

Text #5

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1562086 (Python Code)

Max Activating Token Index: 606

Text #6

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1455152 (Python Code)

Max Activating Token Index: 315

Text #7

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1457045 (Python Code)

Max Activating Token Index: 921

Text #8

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1288895 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 1.0802. Min Range: -1.0802

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1574705 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.9466. Min Act: -0.0000

Data Index: 1440941 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1650873 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1418887 (Python Code)

Max Activating Token Index: 750

Text #13

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1453527 (Python Code)

Max Activating Token Index: 591

Text #14

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1471242 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1419309 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1338787 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1635010 (Python Code)

Max Activating Token Index: 610

Text #18

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1564725 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 1.0802. Min Range: -1.0802

Max Act: 0.7533. Min Act: -0.0000

Data Index: 174476 (C4 (Web Text))

Max Activating Token Index: 486