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

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

Neuron 1591 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: 0.6961. Min Range: -0.6961

Max Act: 0.6961. Min Act: -0.0001

Data Index: 1003654 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6822. Min Act: -0.0001

Data Index: 673540 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.6536. Min Act: -0.0001

Data Index: 6867 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5622. Min Act: -0.0001

Data Index: 563899 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5261. Min Act: -0.0001

Data Index: 1210120 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4654. Min Act: -0.0001

Data Index: 737974 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5000. Min Act: -0.0001

Data Index: 875991 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.5086. Min Act: -0.0001

Data Index: 994709 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4524. Min Act: -0.0001

Data Index: 331120 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4888. Min Act: -0.0001

Data Index: 1332038 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1070934 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1071621 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4617. Min Act: -0.0001

Data Index: 977293 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4430. Min Act: -0.0001

Data Index: 662168 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4505. Min Act: -0.0001

Data Index: 246386 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4407. Min Act: -0.0001

Data Index: 426887 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.3998. Min Act: -0.0001

Data Index: 404539 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4288. Min Act: -0.0001

Data Index: 254775 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.4180. Min Act: -0.0001

Data Index: 226065 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.6961. Min Range: -0.6961

Max Act: 0.3996. Min Act: -0.0001

Data Index: 248512 (C4 (Web Text))

Max Activating Token Index: 266