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

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

Neuron 1059 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1125259 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1329495 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1020. Min Act: -0.0002

Data Index: 665444 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1012. Min Act: -0.0002

Data Index: 501684 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1013. Min Act: -0.0002

Data Index: 530254 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0959. Min Act: -0.0002

Data Index: 668916 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0971. Min Act: -0.0001

Data Index: 402648 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0916. Min Act: -0.0002

Data Index: 999101 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0903. Min Act: -0.0001

Data Index: 62385 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0860. Min Act: -0.0001

Data Index: 18328 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0840. Min Act: -0.0001

Data Index: 164220 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1148756 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0862. Min Act: -0.0002

Data Index: 147475 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0855. Min Act: -0.0002

Data Index: 183778 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0834. Min Act: -0.0002

Data Index: 469064 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0822. Min Act: -0.0002

Data Index: 986017 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0825. Min Act: -0.0002

Data Index: 587352 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0815. Min Act: -0.0002

Data Index: 45056 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0844. Min Act: -0.0002

Data Index: 688685 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0859. Min Act: -0.0001

Data Index: 172834 (C4 (Web Text))

Max Activating Token Index: 396