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

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

Neuron 3085 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.9281. Min Act: 0.0001

Data Index: 271667 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8591. Min Act: -0.0000

Data Index: 801784 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1126464 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8213. Min Act: 0.0000

Data Index: 1137859 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8311. Min Act: -0.0000

Data Index: 577447 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8177. Min Act: -0.0000

Data Index: 205923 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8171. Min Act: -0.0000

Data Index: 682073 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7644. Min Act: -0.0000

Data Index: 593411 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7556. Min Act: -0.0000

Data Index: 560223 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1355082 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7345. Min Act: -0.0000

Data Index: 127221 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7516. Min Act: 0.0001

Data Index: 1132796 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7280. Min Act: -0.0000

Data Index: 870115 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7491. Min Act: -0.0000

Data Index: 768548 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7192. Min Act: -0.0000

Data Index: 227620 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7281. Min Act: -0.0000

Data Index: 919912 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6967. Min Act: -0.0000

Data Index: 841820 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6102. Min Act: -0.0000

Data Index: 942959 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6633. Min Act: -0.0000

Data Index: 671625 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1116334 (C4 (Web Text))

Max Activating Token Index: 139