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

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

Neuron 4094 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1270623 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0736. Min Act: -0.0003

Data Index: 612959 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1176947 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1522395 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0675. Min Act: -0.0003

Data Index: 975021 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1167174 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0632. Min Act: -0.0003

Data Index: 333030 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0647. Min Act: -0.0003

Data Index: 603441 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1105765 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0633. Min Act: -0.0003

Data Index: 998253 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1317980 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1588529 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1059435 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0608. Min Act: -0.0003

Data Index: 360602 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0607. Min Act: -0.0003

Data Index: 769869 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1589940 (Python Code)

Max Activating Token Index: 453

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1420030 (Python Code)

Max Activating Token Index: 308

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0613. Min Act: -0.0003

Data Index: 918045 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1394913 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1593104 (Python Code)

Max Activating Token Index: 805