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

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

Neuron 3479 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5957. Min Range: -2.5957

Max Act: 2.5957. Min Act: -0.0000

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.9836. Min Act: -0.0000

Data Index: 43914 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.7625. Min Act: -0.0000

Data Index: 411940 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6756. Min Act: -0.0000

Data Index: 61227 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6163. Min Act: -0.0000

Data Index: 399293 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.7220. Min Act: -0.0000

Data Index: 1033122 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.8072. Min Act: -0.0000

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6640. Min Act: -0.0000

Data Index: 700070 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1001985 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1353895 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6082. Min Act: -0.0000

Data Index: 243823 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.5802. Min Act: -0.0000

Data Index: 795212 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1357820 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6110. Min Act: -0.0000

Data Index: 950062 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.5700. Min Act: -0.0000

Data Index: 1246640 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6560. Min Act: -0.0000

Data Index: 739422 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.5883. Min Act: -0.0000

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1606940 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.6153. Min Act: -0.0000

Data Index: 419586 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 2.5957. Min Range: -2.5957

Max Act: 1.5344. Min Act: -0.0000

Data Index: 644092 (C4 (Web Text))

Max Activating Token Index: 106