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

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

Neuron 926 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: 0.0966. Min Range: -0.0966

Max Act: 0.0966. Min Act: -0.0006

Data Index: 1438595 (Python Code)

Max Activating Token Index: 312

Text #1

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0898. Min Act: -0.0006

Data Index: 1363124 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0852. Min Act: -0.0006

Data Index: 1582185 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0803. Min Act: -0.0006

Data Index: 1377272 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0799. Min Act: -0.0006

Data Index: 1613381 (Python Code)

Max Activating Token Index: 496

Text #5

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0798. Min Act: -0.0006

Data Index: 1642332 (Python Code)

Max Activating Token Index: 450

Text #6

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0824. Min Act: -0.0005

Data Index: 723664 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0784. Min Act: -0.0006

Data Index: 413396 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0782. Min Act: -0.0006

Data Index: 1555149 (Python Code)

Max Activating Token Index: 269

Text #9

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0761. Min Act: -0.0006

Data Index: 714127 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0750. Min Act: -0.0006

Data Index: 1621209 (Python Code)

Max Activating Token Index: 405

Text #11

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0751. Min Act: -0.0006

Data Index: 886550 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0774. Min Act: -0.0006

Data Index: 1424028 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0773. Min Act: -0.0006

Data Index: 1386866 (Python Code)

Max Activating Token Index: 908

Text #14

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0768. Min Act: -0.0006

Data Index: 1419197 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0767. Min Act: -0.0006

Data Index: 1416543 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0735. Min Act: -0.0006

Data Index: 1546097 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0762. Min Act: -0.0006

Data Index: 1389099 (Python Code)

Max Activating Token Index: 853

Text #18

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0776. Min Act: -0.0005

Data Index: 1110703 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0759. Min Act: -0.0005

Data Index: 1521025 (Python Code)

Max Activating Token Index: 764