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

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

Neuron 2770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1583407 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1457414 (Python Code)

Max Activating Token Index: 518

Text #2

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7427. Min Act: -0.0000

Data Index: 677285 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1517580 (Python Code)

Max Activating Token Index: 761

Text #4

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1568858 (Python Code)

Max Activating Token Index: 847

Text #5

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1597950 (Python Code)

Max Activating Token Index: 577

Text #6

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1370013 (Python Code)

Max Activating Token Index: 865

Text #7

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1374465 (Python Code)

Max Activating Token Index: 711

Text #8

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6916. Min Act: -0.0000

Data Index: 426282 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1543828 (Python Code)

Max Activating Token Index: 198

Text #10

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1538543 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1602108 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1537926 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1393072 (Python Code)

Max Activating Token Index: 655

Text #14

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6442. Min Act: -0.0000

Data Index: 1591373 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1196367 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1495178 (Python Code)

Max Activating Token Index: 779

Text #17

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1419090 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1510316 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 0.9108. Min Range: -0.9108

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1445452 (Python Code)

Max Activating Token Index: 422