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

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

Neuron 3734 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2827. Min Range: -1.2827

Max Act: 1.2827. Min Act: -0.0000

Data Index: 205223 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 1.2827. Min Range: -1.2827

Max Act: 1.1222. Min Act: -0.0000

Data Index: 593158 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1258249 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1177477 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9363. Min Act: -0.0000

Data Index: 552387 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.9979. Min Act: -0.0000

Data Index: 764709 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.8210. Min Act: -0.0000

Data Index: 731076 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.8802. Min Act: -0.0000

Data Index: 226595 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.8675. Min Act: -0.0000

Data Index: 506369 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.8064. Min Act: -0.0000

Data Index: 701259 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7749. Min Act: -0.0000

Data Index: 113014 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7096. Min Act: -0.0000

Data Index: 992637 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7489. Min Act: -0.0000

Data Index: 111474 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7550. Min Act: -0.0000

Data Index: 829279 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7925. Min Act: -0.0001

Data Index: 95016 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7462. Min Act: -0.0000

Data Index: 785971 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7691. Min Act: -0.0000

Data Index: 256362 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1282876 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.7116. Min Act: -0.0000

Data Index: 947056 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.2827. Min Range: -1.2827

Max Act: 0.6644. Min Act: -0.0000

Data Index: 911829 (C4 (Web Text))

Max Activating Token Index: 53