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

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

Neuron 625 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: 1.6697. Min Range: -1.6697

Max Act: 1.6697. Min Act: -0.0000

Data Index: 1561414 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.2949. Min Act: -0.0000

Data Index: 1576612 (Python Code)

Max Activating Token Index: 431

Text #2

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1431766 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.1557. Min Act: -0.0000

Data Index: 1470998 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1363171 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1360754 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1606053 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1444512 (Python Code)

Max Activating Token Index: 994

Text #8

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.0179. Min Act: -0.0000

Data Index: 1492504 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.1087. Min Act: -0.0000

Data Index: 528229 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1591415 (Python Code)

Max Activating Token Index: 980

Text #11

Max Range: 1.6697. Min Range: -1.6697

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1455582 (Python Code)

Max Activating Token Index: 1009

Text #12

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1456647 (Python Code)

Max Activating Token Index: 954

Text #13

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1637232 (Python Code)

Max Activating Token Index: 145

Text #14

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1573721 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9842. Min Act: -0.0000

Data Index: 725778 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1576747 (Python Code)

Max Activating Token Index: 972

Text #17

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1614288 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1533831 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 1.6697. Min Range: -1.6697

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1442241 (Python Code)

Max Activating Token Index: 872