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

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

Neuron 4200 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3604. Min Range: -2.3604

Max Act: 2.2764. Min Act: -0.0000

Data Index: 1395330 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 2.3604. Min Range: -2.3604

Max Act: 2.3604. Min Act: -0.0000

Data Index: 1397514 (Python Code)

Max Activating Token Index: 105

Text #2

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.8960. Min Act: -0.0000

Data Index: 1372663 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.8072. Min Act: -0.0000

Data Index: 1506522 (Python Code)

Max Activating Token Index: 997

Text #4

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.7186. Min Act: -0.0000

Data Index: 1587096 (Python Code)

Max Activating Token Index: 842

Text #5

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.7343. Min Act: -0.0000

Data Index: 1485837 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.6150. Min Act: -0.0000

Data Index: 1411578 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.4683. Min Act: -0.0000

Data Index: 1504399 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1655078 (Python Code)

Max Activating Token Index: 297

Text #9

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1454204 (Python Code)

Max Activating Token Index: 618

Text #10

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.4270. Min Act: -0.0000

Data Index: 1588122 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1398707 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1436758 (Python Code)

Max Activating Token Index: 867

Text #13

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1366307 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1643322 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.3219. Min Act: -0.0000

Data Index: 1630530 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1434680 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1409544 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1516708 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 2.3604. Min Range: -2.3604

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1475793 (Python Code)

Max Activating Token Index: 411