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

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

Neuron 1052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.8883. Min Act: -0.0001

Data Index: 1614373 (Python Code)

Max Activating Token Index: 403

Text #1

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1606455 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1616270 (Python Code)

Max Activating Token Index: 292

Text #3

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9134. Min Act: -0.0001

Data Index: 1640685 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1371075 (Python Code)

Max Activating Token Index: 520

Text #5

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.8250. Min Act: -0.0001

Data Index: 1570742 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1431067 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1409754 (Python Code)

Max Activating Token Index: 279

Text #8

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.8722. Min Act: -0.0001

Data Index: 1387102 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1621357 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1384290 (Python Code)

Max Activating Token Index: 463

Text #11

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9263. Min Act: -0.0001

Data Index: 1641718 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1368237 (Python Code)

Max Activating Token Index: 189

Text #13

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1463344 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1638863 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1540204 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1588729 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1610541 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9702. Min Act: -0.0000

Data Index: 1364945 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.9971. Min Range: -0.9971

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1620028 (Python Code)

Max Activating Token Index: 187