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

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

Neuron 1507 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: 3.5732. Min Range: -3.5732

Max Act: 3.5732. Min Act: -0.0000

Data Index: 1482984 (Python Code)

Max Activating Token Index: 9

Text #1

Max Range: 3.5732. Min Range: -3.5732

Max Act: 3.5540. Min Act: -0.0000

Data Index: 1465563 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 3.5732. Min Range: -3.5732

Max Act: 3.2267. Min Act: -0.0000

Data Index: 1640451 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 3.5732. Min Range: -3.5732

Max Act: 3.0654. Min Act: -0.0000

Data Index: 1412630 (Python Code)

Max Activating Token Index: 477

Text #4

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.6627. Min Act: -0.0000

Data Index: 1465224 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.9681. Min Act: -0.0000

Data Index: 1522791 (Python Code)

Max Activating Token Index: 970

Text #6

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1642175 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.9274. Min Act: -0.0000

Data Index: 1649765 (Python Code)

Max Activating Token Index: 156

Text #8

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.9038. Min Act: -0.0000

Data Index: 1596662 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.7283. Min Act: -0.0000

Data Index: 1619066 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.8833. Min Act: -0.0000

Data Index: 1390408 (Python Code)

Max Activating Token Index: 208

Text #11

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.3372. Min Act: -0.0000

Data Index: 1525924 (Python Code)

Max Activating Token Index: 387

Text #12

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.5566. Min Act: -0.0000

Data Index: 1387741 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.4072. Min Act: -0.0000

Data Index: 1514461 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.2875. Min Act: -0.0000

Data Index: 1496247 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.4929. Min Act: -0.0000

Data Index: 1563120 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.4788. Min Act: -0.0000

Data Index: 1460394 (Python Code)

Max Activating Token Index: 906

Text #17

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.2258. Min Act: -0.0000

Data Index: 1488076 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.4496. Min Act: -0.0000

Data Index: 1571369 (Python Code)

Max Activating Token Index: 512

Text #19

Max Range: 3.5732. Min Range: -3.5732

Max Act: 2.2691. Min Act: -0.0000

Data Index: 1605550 (Python Code)

Max Activating Token Index: 84