Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3608 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.3301. Min Act: -0.0000

Data Index: 93797 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1411765 (Python Code)

Max Activating Token Index: 924

Text #2

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.2933. Min Act: -0.0000

Data Index: 511238 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1385110 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.2457. Min Act: -0.0000

Data Index: 1436124 (Python Code)

Max Activating Token Index: 92

Text #5

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.1580. Min Act: -0.0000

Data Index: 107599 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1442132 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1551168 (Python Code)

Max Activating Token Index: 827

Text #8

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.1693. Min Act: -0.0000

Data Index: 9484 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1370254 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1497393 (Python Code)

Max Activating Token Index: 195

Text #11

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1481259 (Python Code)

Max Activating Token Index: 508

Text #12

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0919. Min Act: -0.0000

Data Index: 58851 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1477425 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1646702 (Python Code)

Max Activating Token Index: 747

Text #15

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0303. Min Act: -0.0000

Data Index: 1478362 (Python Code)

Max Activating Token Index: 655

Text #16

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1562818 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 1.3301. Min Range: -1.3301

Max Act: 1.0189. Min Act: -0.0000

Data Index: 265354 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 1.3301. Min Range: -1.3301

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1584428 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 1.3301. Min Range: -1.3301

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1502057 (Python Code)

Max Activating Token Index: 376