Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4763 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1392266 (Python Code)

Max Activating Token Index: 417

Text #1

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1571886 (Python Code)

Max Activating Token Index: 146

Text #2

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.8566. Min Act: -0.0000

Data Index: 1499424 (Python Code)

Max Activating Token Index: 736

Text #3

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1648427 (Python Code)

Max Activating Token Index: 173

Text #4

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1408612 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1575292 (Python Code)

Max Activating Token Index: 921

Text #6

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1572457 (Python Code)

Max Activating Token Index: 893

Text #7

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.3639. Min Act: -0.0000

Data Index: 1569165 (Python Code)

Max Activating Token Index: 132

Text #8

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1375386 (Python Code)

Max Activating Token Index: 471

Text #9

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.3724. Min Act: -0.0000

Data Index: 1390712 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1587794 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.3263. Min Act: -0.0000

Data Index: 1492460 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1415816 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1587513 (Python Code)

Max Activating Token Index: 139

Text #14

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1580947 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1527207 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.1489. Min Act: -0.0000

Data Index: 1595944 (Python Code)

Max Activating Token Index: 796

Text #17

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1561636 (Python Code)

Max Activating Token Index: 894

Text #18

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1427248 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 1.8566. Min Range: -1.8566

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1432520 (Python Code)

Max Activating Token Index: 10