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

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

Neuron 1005 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: 3.4914. Min Range: -3.4914

Max Act: 3.4914. Min Act: -0.0000

Data Index: 584787 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 3.4914. Min Range: -3.4914

Max Act: 3.4798. Min Act: -0.0000

Data Index: 381394 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 3.4914. Min Range: -3.4914

Max Act: 3.2489. Min Act: -0.0000

Data Index: 1319353 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.9291. Min Act: -0.0000

Data Index: 1026600 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.9073. Min Act: -0.0000

Data Index: 359715 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.8614. Min Act: -0.0000

Data Index: 461916 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.9140. Min Act: -0.0000

Data Index: 127162 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.6466. Min Act: -0.0000

Data Index: 280166 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.5591. Min Act: -0.0000

Data Index: 321699 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.5440. Min Act: -0.0000

Data Index: 56355 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.4934. Min Act: -0.0000

Data Index: 1007972 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.3775. Min Act: -0.0000

Data Index: 1204843 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.1983. Min Act: -0.0000

Data Index: 9040 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.0792. Min Act: -0.0000

Data Index: 27926 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.4914. Min Range: -3.4914

Max Act: 2.0822. Min Act: -0.0000

Data Index: 257084 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.4914. Min Range: -3.4914

Max Act: 1.9669. Min Act: -0.0000

Data Index: 791756 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 3.4914. Min Range: -3.4914

Max Act: 1.9573. Min Act: -0.0000

Data Index: 475244 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 3.4914. Min Range: -3.4914

Max Act: 1.8772. Min Act: -0.0000

Data Index: 871449 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 3.4914. Min Range: -3.4914

Max Act: 1.8545. Min Act: -0.0000

Data Index: 314804 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 3.4914. Min Range: -3.4914

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1019550 (C4 (Web Text))

Max Activating Token Index: 833