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

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

Neuron 4778 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7773. Min Act: -0.0002

Data Index: 722245 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7588. Min Act: -0.0002

Data Index: 736133 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7417. Min Act: -0.0002

Data Index: 606065 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7286. Min Act: -0.0002

Data Index: 1007434 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7158. Min Act: -0.0002

Data Index: 908191 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7137. Min Act: -0.0002

Data Index: 411408 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7270. Min Act: -0.0002

Data Index: 524065 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7192. Min Act: -0.0002

Data Index: 68169 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7151. Min Act: -0.0002

Data Index: 1195579 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7030. Min Act: -0.0002

Data Index: 10552 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6904. Min Act: -0.0002

Data Index: 1096314 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6936. Min Act: -0.0003

Data Index: 586973 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7056. Min Act: -0.0002

Data Index: 753735 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.7052. Min Act: -0.0002

Data Index: 1286426 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6938. Min Act: -0.0002

Data Index: 852088 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6868. Min Act: -0.0002

Data Index: 1224775 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6957. Min Act: -0.0002

Data Index: 888915 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6822. Min Act: -0.0002

Data Index: 1214260 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6795. Min Act: -0.0002

Data Index: 660657 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.7773. Min Range: -0.7773

Max Act: 0.6659. Min Act: -0.0002

Data Index: 675809 (C4 (Web Text))

Max Activating Token Index: 779