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

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

Neuron 2800 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.2162. Min Act: 0.0000

Data Index: 272182 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.1520. Min Act: 0.0000

Data Index: 217620 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.0771. Min Act: 0.0000

Data Index: 128235 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9334. Min Act: 0.0000

Data Index: 917523 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.2162. Min Range: -1.2162

Max Act: 1.0363. Min Act: 0.0000

Data Index: 31917 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9056. Min Act: -0.0000

Data Index: 582533 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1181359 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9285. Min Act: -0.0000

Data Index: 798606 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9175. Min Act: -0.0000

Data Index: 749947 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8504. Min Act: -0.0000

Data Index: 219030 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1249604 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1061556 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8597. Min Act: 0.0000

Data Index: 934216 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8580. Min Act: 0.0000

Data Index: 37860 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.9067. Min Act: 0.0000

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8529. Min Act: 0.0000

Data Index: 789299 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8684. Min Act: 0.0000

Data Index: 507058 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7783. Min Act: 0.0000

Data Index: 249846 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.7878. Min Act: -0.0000

Data Index: 132584 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.2162. Min Range: -1.2162

Max Act: 0.8167. Min Act: 0.0000

Data Index: 890781 (C4 (Web Text))

Max Activating Token Index: 324