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

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

Neuron 4181 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1629039 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1538. Min Act: -0.0000

Data Index: 1436900 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1499864 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1477739 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1596607 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1486872 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1640046 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1571212 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 1.3566. Min Range: -1.3566

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1430200 (Python Code)

Max Activating Token Index: 565

Text #9

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1420291 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1535823 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1362324 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1631936 (Python Code)

Max Activating Token Index: 183

Text #13

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1555651 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1646205 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1363631 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1415629 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1467963 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1648432 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 1.3566. Min Range: -1.3566

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1466116 (Python Code)

Max Activating Token Index: 114