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

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

Neuron 3518 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: 2.2361. Min Range: -2.2361

Max Act: 2.2361. Min Act: -0.0000

Data Index: 975102 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.8389. Min Act: -0.0000

Data Index: 1050283 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1599073 (Python Code)

Max Activating Token Index: 622

Text #3

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.8415. Min Act: -0.0000

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.8306. Min Act: -0.0000

Data Index: 1455937 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.7931. Min Act: -0.0000

Data Index: 1088804 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.6278. Min Act: -0.0000

Data Index: 1142947 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1574905 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.6432. Min Act: -0.0000

Data Index: 377935 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.7787. Min Act: -0.0000

Data Index: 1570844 (Python Code)

Max Activating Token Index: 429

Text #10

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1617361 (Python Code)

Max Activating Token Index: 289

Text #11

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.7798. Min Act: -0.0000

Data Index: 1403495 (Python Code)

Max Activating Token Index: 527

Text #12

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1459949 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.5971. Min Act: -0.0000

Data Index: 1633609 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.7175. Min Act: -0.0000

Data Index: 1530403 (Python Code)

Max Activating Token Index: 603

Text #15

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.6563. Min Act: -0.0000

Data Index: 336457 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.7031. Min Act: -0.0000

Data Index: 1260436 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1232047 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.6260. Min Act: -0.0000

Data Index: 1460099 (Python Code)

Max Activating Token Index: 345

Text #19

Max Range: 2.2361. Min Range: -2.2361

Max Act: 1.5933. Min Act: -0.0000

Data Index: 525759 (C4 (Web Text))

Max Activating Token Index: 839