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

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

Neuron 4353 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8512. Min Act: -0.0000

Data Index: 728919 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7691. Min Act: -0.0000

Data Index: 133472 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7655. Min Act: -0.0000

Data Index: 27290 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7718. Min Act: -0.0000

Data Index: 575957 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1338289 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7775. Min Act: -0.0000

Data Index: 1325565 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7568. Min Act: -0.0000

Data Index: 968502 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8592. Min Act: -0.0000

Data Index: 732786 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6991. Min Act: -0.0000

Data Index: 37198 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.9654. Min Act: -0.0000

Data Index: 864163 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8454. Min Act: -0.0000

Data Index: 900317 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7598. Min Act: -0.0000

Data Index: 386418 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6201. Min Act: -0.0000

Data Index: 180693 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7582. Min Act: -0.0000

Data Index: 1236817 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.8535. Min Act: -0.0000

Data Index: 753524 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.7124. Min Act: -0.0000

Data Index: 787157 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6673. Min Act: -0.0000

Data Index: 626206 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6357. Min Act: -0.0000

Data Index: 1330985 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6681. Min Act: -0.0000

Data Index: 589123 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.9654. Min Range: -1.9654

Max Act: 1.6875. Min Act: -0.0000

Data Index: 384270 (C4 (Web Text))

Max Activating Token Index: 653