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

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

Neuron 2583 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5445. Min Act: -0.0002

Data Index: 1630080 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.5112. Min Act: -0.0002

Data Index: 1396310 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4216. Min Act: -0.0002

Data Index: 1617606 (Python Code)

Max Activating Token Index: 232

Text #3

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4468. Min Act: -0.0002

Data Index: 1530560 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4571. Min Act: -0.0002

Data Index: 1510067 (Python Code)

Max Activating Token Index: 416

Text #5

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4813. Min Act: -0.0002

Data Index: 1580800 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4788. Min Act: -0.0002

Data Index: 1647043 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4748. Min Act: -0.0002

Data Index: 1426900 (Python Code)

Max Activating Token Index: 621

Text #8

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4387. Min Act: -0.0002

Data Index: 1375709 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4540. Min Act: -0.0002

Data Index: 1645056 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4408. Min Act: -0.0002

Data Index: 1639407 (Python Code)

Max Activating Token Index: 194

Text #11

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3990. Min Act: -0.0002

Data Index: 1611681 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3967. Min Act: -0.0002

Data Index: 1414440 (Python Code)

Max Activating Token Index: 714

Text #13

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4278. Min Act: -0.0002

Data Index: 1510516 (Python Code)

Max Activating Token Index: 280

Text #14

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3748. Min Act: -0.0002

Data Index: 1651245 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4282. Min Act: -0.0002

Data Index: 1412328 (Python Code)

Max Activating Token Index: 408

Text #16

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4284. Min Act: -0.0002

Data Index: 1518224 (Python Code)

Max Activating Token Index: 198

Text #17

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3988. Min Act: -0.0002

Data Index: 1433206 (Python Code)

Max Activating Token Index: 621

Text #18

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.4086. Min Act: -0.0002

Data Index: 1489561 (Python Code)

Max Activating Token Index: 27

Text #19

Max Range: 0.5445. Min Range: -0.5445

Max Act: 0.3715. Min Act: -0.0002

Data Index: 1513140 (Python Code)

Max Activating Token Index: 564