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

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

Neuron 656 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: 2.0654. Min Range: -2.0654

Max Act: 2.0089. Min Act: -0.0000

Data Index: 1392007 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 2.0654. Min Range: -2.0654

Max Act: 2.0654. Min Act: -0.0000

Data Index: 1484258 (Python Code)

Max Activating Token Index: 769

Text #2

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6036. Min Act: -0.0000

Data Index: 1652266 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.7951. Min Act: -0.0000

Data Index: 1448906 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1455154 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.8659. Min Act: -0.0000

Data Index: 1504627 (Python Code)

Max Activating Token Index: 152

Text #6

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.8693. Min Act: -0.0000

Data Index: 1376626 (Python Code)

Max Activating Token Index: 915

Text #7

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6553. Min Act: -0.0000

Data Index: 1406601 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1375039 (Python Code)

Max Activating Token Index: 814

Text #9

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1415862 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1386570 (Python Code)

Max Activating Token Index: 867

Text #11

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1423615 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6088. Min Act: -0.0000

Data Index: 1476406 (Python Code)

Max Activating Token Index: 352

Text #13

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5957. Min Act: -0.0000

Data Index: 1410027 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5001. Min Act: -0.0000

Data Index: 1495585 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1538603 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1628916 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1616038 (Python Code)

Max Activating Token Index: 938

Text #18

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5627. Min Act: -0.0000

Data Index: 1629826 (Python Code)

Max Activating Token Index: 642

Text #19

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1594870 (Python Code)

Max Activating Token Index: 631