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

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

Neuron 4911 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: 2.7647. Min Range: -2.7647

Max Act: 2.6182. Min Act: -0.0000

Data Index: 1363014 (Python Code)

Max Activating Token Index: 585

Text #1

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.7647. Min Act: -0.0000

Data Index: 1571109 (Python Code)

Max Activating Token Index: 630

Text #2

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.6315. Min Act: -0.0000

Data Index: 1460299 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.3499. Min Act: -0.0000

Data Index: 1634313 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.4224. Min Act: -0.0000

Data Index: 1468013 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.4205. Min Act: -0.0000

Data Index: 1565949 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.2593. Min Act: -0.0000

Data Index: 1629998 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.6207. Min Act: -0.0000

Data Index: 1633161 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.4887. Min Act: -0.0000

Data Index: 1481732 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.3662. Min Act: -0.0000

Data Index: 1635637 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.2371. Min Act: -0.0000

Data Index: 1446402 (Python Code)

Max Activating Token Index: 853

Text #11

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.3560. Min Act: -0.0000

Data Index: 1452045 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.2393. Min Act: -0.0000

Data Index: 1458657 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.1573. Min Act: -0.0000

Data Index: 1496575 (Python Code)

Max Activating Token Index: 631

Text #14

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.1150. Min Act: -0.0000

Data Index: 1517017 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.1844. Min Act: -0.0000

Data Index: 1369712 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 2.7647. Min Range: -2.7647

Max Act: 2.0380. Min Act: -0.0000

Data Index: 1455109 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 2.7647. Min Range: -2.7647

Max Act: 1.9397. Min Act: -0.0000

Data Index: 1644998 (Python Code)

Max Activating Token Index: 420

Text #18

Max Range: 2.7647. Min Range: -2.7647

Max Act: 1.9198. Min Act: -0.0000

Data Index: 1466775 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 2.7647. Min Range: -2.7647

Max Act: 1.7618. Min Act: -0.0000

Data Index: 1459502 (Python Code)

Max Activating Token Index: 255