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

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

Neuron 3137 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.2992. Min Act: -0.0000

Data Index: 993966 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1837. Min Act: -0.0001

Data Index: 899117 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.1362. Min Act: -0.0000

Data Index: 1154126 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.2992. Min Range: -1.2992

Max Act: 1.0130. Min Act: -0.0001

Data Index: 1030016 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9228. Min Act: -0.0000

Data Index: 258594 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9255. Min Act: -0.0000

Data Index: 974351 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.9110. Min Act: -0.0001

Data Index: 1048391 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.8592. Min Act: -0.0000

Data Index: 272747 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.8844. Min Act: -0.0000

Data Index: 292453 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.8588. Min Act: -0.0000

Data Index: 18321 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.8442. Min Act: -0.0001

Data Index: 85797 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.8676. Min Act: -0.0000

Data Index: 241588 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1097611 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1212050 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.7559. Min Act: -0.0000

Data Index: 177482 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.7906. Min Act: -0.0000

Data Index: 523571 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.7838. Min Act: -0.0001

Data Index: 1100846 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.7947. Min Act: -0.0000

Data Index: 561427 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.7660. Min Act: -0.0001

Data Index: 858653 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.2992. Min Range: -1.2992

Max Act: 0.8309. Min Act: -0.0000

Data Index: 8052 (C4 (Web Text))

Max Activating Token Index: 899