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

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

Neuron 3707 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1174694 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1628243 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1633176 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1521517 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1431889 (Python Code)

Max Activating Token Index: 233

Text #5

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1637. Min Act: -0.0000

Data Index: 298997 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1117156 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1145208 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1437. Min Act: 0.0000

Data Index: 1600607 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1389910 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1441791 (Python Code)

Max Activating Token Index: 182

Text #11

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1527109 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1227. Min Act: -0.0000

Data Index: 581433 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1426. Min Act: -0.0000

Data Index: 779676 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1534658 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1428. Min Act: -0.0000

Data Index: 1374760 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1459. Min Act: -0.0000

Data Index: 496197 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1457863 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1628758 (Python Code)

Max Activating Token Index: 421

Text #19

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1033680 (C4 (Web Text))

Max Activating Token Index: 400