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

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

Neuron 1908 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.5853. Min Act: -0.0000

Data Index: 881436 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2427. Min Act: -0.0000

Data Index: 560642 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2728. Min Act: -0.0000

Data Index: 795100 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2563. Min Act: -0.0000

Data Index: 684648 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.2199. Min Act: -0.0000

Data Index: 926300 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1024068 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1840. Min Act: -0.0000

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1729. Min Act: -0.0000

Data Index: 905977 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1309. Min Act: -0.0000

Data Index: 342047 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0939. Min Act: -0.0000

Data Index: 1255849 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1331. Min Act: -0.0000

Data Index: 1251242 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1014. Min Act: -0.0000

Data Index: 145385 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0681. Min Act: -0.0000

Data Index: 523948 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.9907. Min Act: -0.0000

Data Index: 303410 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.1139. Min Act: -0.0000

Data Index: 239586 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0064. Min Act: -0.0000

Data Index: 37182 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.9932. Min Act: -0.0000

Data Index: 748985 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 1.5853. Min Range: -1.5853

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1237360 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.5853. Min Range: -1.5853

Max Act: 1.0077. Min Act: -0.0000

Data Index: 28560 (C4 (Web Text))

Max Activating Token Index: 895