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

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

Neuron 454 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.7684. Min Act: -0.0000

Data Index: 1401016 (Python Code)

Max Activating Token Index: 490

Text #1

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6771. Min Act: -0.0000

Data Index: 1171868 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.6988. Min Act: -0.0000

Data Index: 1096967 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.5874. Min Act: -0.0000

Data Index: 1615504 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1635027 (Python Code)

Max Activating Token Index: 209

Text #5

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.4471. Min Act: -0.0000

Data Index: 1597453 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1545027 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.3889. Min Act: 0.0000

Data Index: 1399193 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1473622 (Python Code)

Max Activating Token Index: 451

Text #9

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1527582 (Python Code)

Max Activating Token Index: 184

Text #10

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1554772 (Python Code)

Max Activating Token Index: 661

Text #11

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1617484 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1468. Min Act: -0.0000

Data Index: 1563665 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1614765 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1410977 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1705. Min Act: 0.0000

Data Index: 1426208 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1481255 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 1.7684. Min Range: -1.7684

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1558395 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1487003 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 1.7684. Min Range: -1.7684

Max Act: 1.0310. Min Act: 0.0000

Data Index: 1388146 (Python Code)

Max Activating Token Index: 112