Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2101. Min Act: -0.0001

Data Index: 981436 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2018. Min Act: -0.0001

Data Index: 673664 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2051. Min Act: -0.0001

Data Index: 754391 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1771. Min Act: -0.0000

Data Index: 236883 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1604. Min Act: -0.0001

Data Index: 409807 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1638. Min Act: -0.0000

Data Index: 584013 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1678. Min Act: -0.0000

Data Index: 678822 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1621. Min Act: -0.0000

Data Index: 620098 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1795. Min Act: -0.0001

Data Index: 792597 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1711. Min Act: -0.0000

Data Index: 73928 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1596. Min Act: -0.0001

Data Index: 766940 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1279708 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1099419 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1580. Min Act: -0.0001

Data Index: 661277 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1411013 (Python Code)

Max Activating Token Index: 754

Text #15

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1614. Min Act: -0.0001

Data Index: 43049 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1629. Min Act: -0.0000

Data Index: 848043 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1498. Min Act: -0.0000

Data Index: 756387 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1007057 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1477. Min Act: -0.0000

Data Index: 162166 (C4 (Web Text))

Max Activating Token Index: 654