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

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

Neuron 3766 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.8679. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.6006. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.4015. Min Act: -0.0000

Data Index: 150884 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.5664. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.3934. Min Act: -0.0000

Data Index: 533852 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.3561. Min Act: -0.0000

Data Index: 989529 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.1875. Min Act: -0.0000

Data Index: 237344 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.3603. Min Act: -0.0000

Data Index: 876054 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.2359. Min Act: -0.0000

Data Index: 1322910 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.2490. Min Act: -0.0000

Data Index: 527953 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.2049. Min Act: -0.0000

Data Index: 845959 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.2007. Min Act: -0.0000

Data Index: 576164 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.1581. Min Act: -0.0000

Data Index: 1347565 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.1013. Min Act: -0.0000

Data Index: 327084 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 2.8679. Min Range: -2.8679

Max Act: 1.8926. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.0579. Min Act: -0.0000

Data Index: 1022382 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 2.8679. Min Range: -2.8679

Max Act: 1.9220. Min Act: -0.0000

Data Index: 1074542 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.0612. Min Act: -0.0000

Data Index: 629533 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.1519. Min Act: -0.0000

Data Index: 530989 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 2.8679. Min Range: -2.8679

Max Act: 2.0118. Min Act: -0.0000

Data Index: 1025964 (C4 (Web Text))

Max Activating Token Index: 256