Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2405 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0654. Min Range: -2.0654

Max Act: 2.0654. Min Act: -0.0000

Data Index: 339943 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.9625. Min Act: -0.0000

Data Index: 643990 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6621. Min Act: -0.0000

Data Index: 792770 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.7591. Min Act: -0.0000

Data Index: 1449289 (Python Code)

Max Activating Token Index: 988

Text #4

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5886. Min Act: -0.0000

Data Index: 1300933 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6656. Min Act: -0.0000

Data Index: 1205765 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6638. Min Act: -0.0000

Data Index: 457004 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1605911 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1372973 (Python Code)

Max Activating Token Index: 901

Text #9

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4969. Min Act: -0.0000

Data Index: 1645494 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4846. Min Act: -0.0000

Data Index: 1620731 (Python Code)

Max Activating Token Index: 516

Text #11

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4778. Min Act: -0.0000

Data Index: 1038844 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.3796. Min Act: -0.0000

Data Index: 360379 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.5232. Min Act: -0.0000

Data Index: 1551419 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4138. Min Act: -0.0000

Data Index: 508595 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.4138. Min Act: -0.0000

Data Index: 583751 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.3912. Min Act: -0.0000

Data Index: 112366 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1514978 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.3543. Min Act: -0.0000

Data Index: 443098 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 2.0654. Min Range: -2.0654

Max Act: 1.3117. Min Act: -0.0000

Data Index: 733841 (C4 (Web Text))

Max Activating Token Index: 147