Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2362 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1069. Min Act: -0.0003

Data Index: 167874 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1059. Min Act: -0.0003

Data Index: 111636 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1101. Min Act: -0.0003

Data Index: 621786 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1031. Min Act: -0.0003

Data Index: 603251 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1011. Min Act: -0.0003

Data Index: 365079 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0935. Min Act: -0.0003

Data Index: 1293560 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0952. Min Act: -0.0003

Data Index: 82864 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0987. Min Act: -0.0003

Data Index: 502490 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1008. Min Act: -0.0003

Data Index: 60101 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0984. Min Act: -0.0003

Data Index: 490748 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0917. Min Act: -0.0003

Data Index: 1152693 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0959. Min Act: -0.0003

Data Index: 985058 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0904. Min Act: -0.0003

Data Index: 465336 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0832. Min Act: -0.0003

Data Index: 51802 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0971. Min Act: -0.0003

Data Index: 1072885 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0945. Min Act: -0.0003

Data Index: 1118051 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0913. Min Act: -0.0003

Data Index: 924504 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0919. Min Act: -0.0003

Data Index: 1100438 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1000533 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0942. Min Act: -0.0003

Data Index: 921679 (C4 (Web Text))

Max Activating Token Index: 69