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

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

Neuron 2016 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1301. Min Range: -2.1301

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1520716 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 2.1301. Min Range: -2.1301

Max Act: 2.0081. Min Act: -0.0000

Data Index: 1389103 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 2.1301. Min Range: -2.1301

Max Act: 2.1301. Min Act: -0.0000

Data Index: 1391103 (Python Code)

Max Activating Token Index: 474

Text #3

Max Range: 2.1301. Min Range: -2.1301

Max Act: 2.0840. Min Act: -0.0000

Data Index: 1617494 (Python Code)

Max Activating Token Index: 528

Text #4

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.8831. Min Act: -0.0000

Data Index: 1616622 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.6470. Min Act: -0.0000

Data Index: 1394557 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.9064. Min Act: -0.0000

Data Index: 1458562 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.8205. Min Act: -0.0000

Data Index: 1625065 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.5845. Min Act: -0.0000

Data Index: 1537754 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.6749. Min Act: -0.0000

Data Index: 1508957 (Python Code)

Max Activating Token Index: 1003

Text #10

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.6561. Min Act: -0.0000

Data Index: 1390176 (Python Code)

Max Activating Token Index: 725

Text #11

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.7333. Min Act: -0.0000

Data Index: 1516958 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.5963. Min Act: -0.0000

Data Index: 1467229 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.6005. Min Act: -0.0000

Data Index: 1651826 (Python Code)

Max Activating Token Index: 635

Text #14

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.5737. Min Act: -0.0000

Data Index: 1480647 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.6426. Min Act: -0.0000

Data Index: 1463529 (Python Code)

Max Activating Token Index: 820

Text #16

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1650012 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.5901. Min Act: -0.0000

Data Index: 1438772 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1644511 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 2.1301. Min Range: -2.1301

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1549158 (Python Code)

Max Activating Token Index: 281