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

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

Neuron 1791 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1037608 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1138677 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0858. Min Act: -0.0001

Data Index: 901679 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0769. Min Act: -0.0001

Data Index: 384993 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0799. Min Act: -0.0001

Data Index: 177027 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0733. Min Act: -0.0001

Data Index: 690095 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0704. Min Act: -0.0001

Data Index: 61260 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1230584 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0724. Min Act: -0.0001

Data Index: 102072 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0688. Min Act: -0.0001

Data Index: 152930 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0625. Min Act: -0.0001

Data Index: 969446 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0676. Min Act: -0.0001

Data Index: 840269 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0669. Min Act: -0.0001

Data Index: 885955 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1283749 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0644. Min Act: -0.0001

Data Index: 796278 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0660. Min Act: -0.0001

Data Index: 1459301 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0635. Min Act: -0.0001

Data Index: 935733 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0627. Min Act: -0.0001

Data Index: 930563 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0645. Min Act: -0.0001

Data Index: 430435 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1374595 (Python Code)

Max Activating Token Index: 330