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

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

Neuron 4574 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0030. Min Act: -0.0001

Data Index: 1631945 (Python Code)

Max Activating Token Index: 878

Text #1

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0025. Min Act: -0.0001

Data Index: 1370869 (Python Code)

Max Activating Token Index: 672

Text #2

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0025. Min Act: -0.0002

Data Index: 1288767 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0025. Min Act: -0.0001

Data Index: 1639409 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0025. Min Act: -0.0001

Data Index: 1470823 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0023. Min Act: -0.0001

Data Index: 1541512 (Python Code)

Max Activating Token Index: 514

Text #6

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0023. Min Act: -0.0002

Data Index: 1390184 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0001

Data Index: 1508699 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0023. Min Act: -0.0002

Data Index: 1343784 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1363479 (Python Code)

Max Activating Token Index: 831

Text #10

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0002

Data Index: 934790 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0001

Data Index: 1469067 (Python Code)

Max Activating Token Index: 423

Text #12

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0023. Min Act: -0.0001

Data Index: 1500478 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0001

Data Index: 1420105 (Python Code)

Max Activating Token Index: 487

Text #14

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0001

Data Index: 233520 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1639989 (Python Code)

Max Activating Token Index: 513

Text #16

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0021. Min Act: -0.0001

Data Index: 1493144 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0021. Min Act: -0.0001

Data Index: 1375013 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0020. Min Act: -0.0002

Data Index: 1380218 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 0.0030. Min Range: -0.0030

Max Act: 0.0021. Min Act: -0.0001

Data Index: 1514272 (Python Code)

Max Activating Token Index: 787