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

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

Neuron 1186 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: 0.0897. Min Range: -0.0897

Max Act: 0.0897. Min Act: -0.0001

Data Index: 495614 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1357121 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0773. Min Act: -0.0000

Data Index: 719654 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0777. Min Act: -0.0000

Data Index: 59156 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1121774 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0740. Min Act: -0.0001

Data Index: 974908 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0770. Min Act: -0.0000

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1143912 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1602836 (Python Code)

Max Activating Token Index: 540

Text #9

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1635519 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0666. Min Act: -0.0000

Data Index: 684327 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0701. Min Act: -0.0001

Data Index: 295123 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0711. Min Act: -0.0001

Data Index: 719369 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0662. Min Act: -0.0000

Data Index: 278254 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1459395 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1352438 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1111787 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0664. Min Act: -0.0000

Data Index: 488487 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0685. Min Act: -0.0000

Data Index: 717159 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1102269 (C4 (Web Text))

Max Activating Token Index: 611