Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 6 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0712. Min Act: -0.0006

Data Index: 633573 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0726. Min Act: -0.0005

Data Index: 495028 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0719. Min Act: -0.0006

Data Index: 534978 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0720. Min Act: -0.0006

Data Index: 211828 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0704. Min Act: -0.0005

Data Index: 199650 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0675. Min Act: -0.0005

Data Index: 154974 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0670. Min Act: -0.0006

Data Index: 787034 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0719. Min Act: -0.0006

Data Index: 786449 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0691. Min Act: -0.0006

Data Index: 504885 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0683. Min Act: -0.0005

Data Index: 740143 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0677. Min Act: -0.0006

Data Index: 14767 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0676. Min Act: -0.0006

Data Index: 58875 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0651. Min Act: -0.0005

Data Index: 1213824 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0006

Data Index: 27815 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0669. Min Act: -0.0006

Data Index: 946785 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0690. Min Act: -0.0005

Data Index: 988867 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0719. Min Act: -0.0006

Data Index: 1009405 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0661. Min Act: -0.0006

Data Index: 1067963 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0656. Min Act: -0.0006

Data Index: 565791 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0674. Min Act: -0.0006

Data Index: 1196232 (C4 (Web Text))

Max Activating Token Index: 500