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

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

Neuron 4206 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: 1.8211. Min Range: -1.8211

Max Act: 1.8211. Min Act: -0.0000

Data Index: 1026208 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.7065. Min Act: -0.0000

Data Index: 53098 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.6799. Min Act: -0.0000

Data Index: 1288425 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.5585. Min Act: -0.0000

Data Index: 108301 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.4278. Min Act: -0.0000

Data Index: 743870 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.4720. Min Act: -0.0000

Data Index: 529928 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.2926. Min Act: -0.0000

Data Index: 56709 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.4005. Min Act: -0.0000

Data Index: 307831 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1395515 (Python Code)

Max Activating Token Index: 777

Text #9

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.4173. Min Act: -0.0000

Data Index: 987532 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.1684. Min Act: -0.0000

Data Index: 9613 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.3897. Min Act: -0.0000

Data Index: 175825 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.3782. Min Act: -0.0000

Data Index: 377718 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1543700 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 1.8211. Min Range: -1.8211

Max Act: 0.6913. Min Act: -0.0000

Data Index: 611197 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.3388. Min Act: -0.0000

Data Index: 1205011 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1104929 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1045443 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.1784. Min Act: -0.0000

Data Index: 701384 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 1.8211. Min Range: -1.8211

Max Act: 1.2949. Min Act: -0.0000

Data Index: 11858 (C4 (Web Text))

Max Activating Token Index: 13