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

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

Neuron 702 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.0266. Min Range: -9.0266

Max Act: 9.0266. Min Act: -0.0000

Data Index: 1441226 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 9.0266. Min Range: -9.0266

Max Act: 8.9394. Min Act: -0.0000

Data Index: 1433604 (Python Code)

Max Activating Token Index: 965

Text #2

Max Range: 9.0266. Min Range: -9.0266

Max Act: 8.3728. Min Act: -0.0000

Data Index: 1386219 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 9.0266. Min Range: -9.0266

Max Act: 8.0372. Min Act: -0.0000

Data Index: 1481313 (Python Code)

Max Activating Token Index: 763

Text #4

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.5974. Min Act: -0.0000

Data Index: 1597677 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.5036. Min Act: -0.0000

Data Index: 1543154 (Python Code)

Max Activating Token Index: 350

Text #6

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.2314. Min Act: -0.0000

Data Index: 1616904 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.3685. Min Act: -0.0000

Data Index: 1555612 (Python Code)

Max Activating Token Index: 698

Text #8

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.6691. Min Act: -0.0000

Data Index: 1450804 (Python Code)

Max Activating Token Index: 605

Text #9

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.0834. Min Act: -0.0000

Data Index: 1653592 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.3944. Min Act: -0.0000

Data Index: 1593494 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.5598. Min Act: -0.0000

Data Index: 1396013 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.2234. Min Act: -0.0000

Data Index: 1575767 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.5185. Min Act: -0.0000

Data Index: 1547195 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.3332. Min Act: -0.0000

Data Index: 1368798 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.2990. Min Act: -0.0000

Data Index: 1497895 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.4744. Min Act: -0.0000

Data Index: 1366578 (Python Code)

Max Activating Token Index: 805

Text #17

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.2688. Min Act: -0.0000

Data Index: 1548324 (Python Code)

Max Activating Token Index: 390

Text #18

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.2335. Min Act: -0.0000

Data Index: 1544353 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 9.0266. Min Range: -9.0266

Max Act: 7.0619. Min Act: -0.0000

Data Index: 1418609 (Python Code)

Max Activating Token Index: 61