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

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

Neuron 635 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.3660. Min Act: -0.0000

Data Index: 1595452 (Python Code)

Max Activating Token Index: 305

Text #1

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.8926. Min Act: -0.0000

Data Index: 1382487 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.2271. Min Act: -0.0000

Data Index: 1475198 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.3282. Min Act: -0.0000

Data Index: 1420626 (Python Code)

Max Activating Token Index: 342

Text #4

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.2072. Min Act: -0.0000

Data Index: 1543847 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.1990. Min Act: -0.0000

Data Index: 951508 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.9474. Min Act: -0.0000

Data Index: 1656181 (Python Code)

Max Activating Token Index: 598

Text #7

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.2004. Min Act: -0.0000

Data Index: 1391670 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.2017. Min Act: -0.0000

Data Index: 1570471 (Python Code)

Max Activating Token Index: 319

Text #9

Max Range: 2.3660. Min Range: -2.3660

Max Act: 2.0587. Min Act: -0.0000

Data Index: 1434191 (Python Code)

Max Activating Token Index: 494

Text #10

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.9378. Min Act: -0.0000

Data Index: 1545339 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.8938. Min Act: -0.0000

Data Index: 1548139 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1398927 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.9108. Min Act: -0.0000

Data Index: 1496537 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.7978. Min Act: -0.0000

Data Index: 1467457 (Python Code)

Max Activating Token Index: 756

Text #15

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.6648. Min Act: -0.0000

Data Index: 1473151 (Python Code)

Max Activating Token Index: 251

Text #16

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.8644. Min Act: -0.0000

Data Index: 1446270 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.7516. Min Act: -0.0000

Data Index: 395859 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.8275. Min Act: -0.0000

Data Index: 1458217 (Python Code)

Max Activating Token Index: 537

Text #19

Max Range: 2.3660. Min Range: -2.3660

Max Act: 1.7347. Min Act: -0.0000

Data Index: 1389373 (Python Code)

Max Activating Token Index: 534