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

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

Neuron 3581 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.5058. Min Act: -0.0001

Data Index: 752841 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.8186. Min Act: -0.0001

Data Index: 815515 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.4616. Min Act: -0.0001

Data Index: 257952 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.4211. Min Act: -0.0001

Data Index: 209206 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.4092. Min Act: -0.0001

Data Index: 249805 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.2902. Min Act: -0.0001

Data Index: 62105 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 1.8186. Min Range: -1.8186

Max Act: 0.9838. Min Act: -0.0001

Data Index: 596146 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.1111. Min Act: -0.0001

Data Index: 1141848 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.1855. Min Act: -0.0001

Data Index: 566675 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.1325. Min Act: -0.0001

Data Index: 88607 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.1200. Min Act: -0.0001

Data Index: 1221634 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.1196. Min Act: -0.0001

Data Index: 956263 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.1142. Min Act: -0.0001

Data Index: 30565 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.0735. Min Act: -0.0001

Data Index: 374277 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.1026. Min Act: -0.0001

Data Index: 1349321 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.0589. Min Act: -0.0001

Data Index: 1036130 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.0178. Min Act: -0.0001

Data Index: 1260505 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.0445. Min Act: -0.0001

Data Index: 158615 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.0624. Min Act: -0.0001

Data Index: 1063472 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.8186. Min Range: -1.8186

Max Act: 1.0218. Min Act: -0.0001

Data Index: 395729 (C4 (Web Text))

Max Activating Token Index: 293