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

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

Neuron 107 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8237. Min Act: -0.0001

Data Index: 533164 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7879. Min Act: -0.0001

Data Index: 1213992 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7620. Min Act: -0.0001

Data Index: 139774 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7495. Min Act: -0.0001

Data Index: 1114102 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8103. Min Act: -0.0001

Data Index: 364599 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7845. Min Act: -0.0001

Data Index: 1278008 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8088. Min Act: -0.0001

Data Index: 270238 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7107. Min Act: -0.0001

Data Index: 61118 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7190. Min Act: -0.0001

Data Index: 1260442 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7210. Min Act: -0.0001

Data Index: 440017 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6873. Min Act: -0.0001

Data Index: 136840 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6763. Min Act: -0.0001

Data Index: 87632 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6700. Min Act: -0.0001

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6910. Min Act: -0.0001

Data Index: 250175 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6888. Min Act: -0.0001

Data Index: 792577 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6609. Min Act: -0.0001

Data Index: 926462 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7047. Min Act: -0.0001

Data Index: 890435 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6827. Min Act: -0.0001

Data Index: 889521 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1043342 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6231. Min Act: -0.0001

Data Index: 1314852 (C4 (Web Text))

Max Activating Token Index: 960