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

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

Neuron 837 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.7768. Min Act: -0.0000

Data Index: 55513 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.7411. Min Act: -0.0000

Data Index: 925009 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6914. Min Act: -0.0000

Data Index: 616935 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6791. Min Act: -0.0000

Data Index: 551073 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1040787 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.7142. Min Act: -0.0001

Data Index: 792061 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1354336 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.7107. Min Act: -0.0000

Data Index: 15878 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1038788 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1325616 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1110924 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1050360 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.7001. Min Act: -0.0000

Data Index: 529666 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.5868. Min Act: -0.0000

Data Index: 690226 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6093. Min Act: -0.0001

Data Index: 637863 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6218. Min Act: -0.0000

Data Index: 61055 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.5872. Min Act: -0.0000

Data Index: 958441 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.6161. Min Act: -0.0000

Data Index: 601293 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.5491. Min Act: -0.0000

Data Index: 409517 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.7768. Min Range: -0.7768

Max Act: 0.5838. Min Act: -0.0000

Data Index: 676345 (C4 (Web Text))

Max Activating Token Index: 901