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

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

Neuron 278 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0002

Data Index: 307024 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1273826 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0733. Min Act: -0.0002

Data Index: 131019 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0756. Min Act: -0.0002

Data Index: 328796 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0713. Min Act: -0.0002

Data Index: 780670 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0710. Min Act: -0.0002

Data Index: 801775 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0685. Min Act: -0.0002

Data Index: 238795 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0657. Min Act: -0.0002

Data Index: 659822 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0653. Min Act: -0.0002

Data Index: 228202 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0676. Min Act: -0.0002

Data Index: 238405 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0655. Min Act: -0.0002

Data Index: 371038 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0627. Min Act: -0.0002

Data Index: 824220 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0647. Min Act: -0.0002

Data Index: 643135 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1072158 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0602. Min Act: -0.0002

Data Index: 106038 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1279225 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0585. Min Act: -0.0002

Data Index: 801611 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0588. Min Act: -0.0002

Data Index: 768136 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0573. Min Act: -0.0002

Data Index: 135795 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0572. Min Act: -0.0002

Data Index: 918966 (C4 (Web Text))

Max Activating Token Index: 224