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

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

Neuron 2873 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0817. Min Act: -0.0002

Data Index: 647552 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0749. Min Act: -0.0002

Data Index: 613249 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1386926 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1617379 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0679. Min Act: -0.0002

Data Index: 483495 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1205875 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0668. Min Act: -0.0002

Data Index: 533232 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1341259 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0653. Min Act: -0.0002

Data Index: 514954 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1071396 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0637. Min Act: -0.0002

Data Index: 704567 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1575285 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1392775 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1366637 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0566. Min Act: -0.0002

Data Index: 409586 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0634. Min Act: -0.0002

Data Index: 777396 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0566. Min Act: -0.0002

Data Index: 503194 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0599. Min Act: -0.0002

Data Index: 707363 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1147737 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0817. Min Range: -0.0817

Max Act: 0.0557. Min Act: -0.0002

Data Index: 599524 (C4 (Web Text))

Max Activating Token Index: 945