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

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

Neuron 5392 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0526. Min Range: -1.0526

Max Act: 1.0526. Min Act: -0.0000

Data Index: 562866 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.9824. Min Act: -0.0000

Data Index: 550502 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1258584 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.9063. Min Act: -0.0000

Data Index: 184196 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.8985. Min Act: -0.0000

Data Index: 566944 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.8990. Min Act: -0.0000

Data Index: 167649 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1311873 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.8254. Min Act: -0.0000

Data Index: 272491 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.8169. Min Act: -0.0000

Data Index: 599622 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7879. Min Act: -0.0000

Data Index: 348990 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7848. Min Act: -0.0000

Data Index: 917845 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.8090. Min Act: -0.0000

Data Index: 276326 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.8241. Min Act: -0.0000

Data Index: 165255 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1103457 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7456. Min Act: -0.0000

Data Index: 567545 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7625. Min Act: -0.0000

Data Index: 300319 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7443. Min Act: -0.0000

Data Index: 54579 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7185. Min Act: -0.0000

Data Index: 58339 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1083311 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.0526. Min Range: -1.0526

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1035293 (C4 (Web Text))

Max Activating Token Index: 308