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

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

Neuron 1975 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3095. Min Range: -3.3095

Max Act: 3.3095. Min Act: -0.0000

Data Index: 1158907 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.2210. Min Act: -0.0000

Data Index: 978482 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.1258. Min Act: -0.0000

Data Index: 779766 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.0978. Min Act: -0.0000

Data Index: 732536 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1345187 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.9273. Min Act: -0.0000

Data Index: 793040 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.0370. Min Act: -0.0000

Data Index: 478260 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.1510. Min Act: -0.0000

Data Index: 937220 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.8941. Min Act: -0.0000

Data Index: 197550 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.0005. Min Act: -0.0000

Data Index: 1079714 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.0533. Min Act: -0.0000

Data Index: 1342554 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.0012. Min Act: -0.0000

Data Index: 238963 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.7879. Min Act: -0.0000

Data Index: 288640 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 3.3095. Min Range: -3.3095

Max Act: 2.0019. Min Act: -0.0000

Data Index: 823839 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.9005. Min Act: -0.0000

Data Index: 1144242 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.8654. Min Act: -0.0000

Data Index: 12465 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.8257. Min Act: -0.0000

Data Index: 1198400 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.8083. Min Act: -0.0000

Data Index: 850412 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.8011. Min Act: -0.0000

Data Index: 286320 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.3095. Min Range: -3.3095

Max Act: 1.8022. Min Act: -0.0000

Data Index: 1279917 (C4 (Web Text))

Max Activating Token Index: 406