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

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

Neuron 2415 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1540659 (Python Code)

Max Activating Token Index: 333

Text #1

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6344. Min Act: 0.0000

Data Index: 1584237 (Python Code)

Max Activating Token Index: 991

Text #2

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1509260 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1592284 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5774. Min Act: 0.0000

Data Index: 1627367 (Python Code)

Max Activating Token Index: 975

Text #5

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.5650. Min Act: 0.0000

Data Index: 1556911 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1548271 (Python Code)

Max Activating Token Index: 583

Text #7

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4431. Min Act: 0.0000

Data Index: 1390440 (Python Code)

Max Activating Token Index: 831

Text #8

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1452356 (Python Code)

Max Activating Token Index: 100

Text #9

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1635261 (Python Code)

Max Activating Token Index: 469

Text #10

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1360589 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1495077 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1573023 (Python Code)

Max Activating Token Index: 93

Text #13

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1542463 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1621334 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4157. Min Act: 0.0000

Data Index: 1385542 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4162. Min Act: -0.0000

Data Index: 873374 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1557132 (Python Code)

Max Activating Token Index: 542

Text #18

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1458142 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 0.6637. Min Range: -0.6637

Max Act: 0.4037. Min Act: -0.0000

Data Index: 984260 (C4 (Web Text))

Max Activating Token Index: 1019