Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1245. Min Act: -0.0001

Data Index: 590927 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1485233 (Python Code)

Max Activating Token Index: 820

Text #2

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1146932 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1109. Min Act: -0.0001

Data Index: 136628 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1547882 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1004. Min Act: -0.0001

Data Index: 487436 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0985. Min Act: -0.0001

Data Index: 518823 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1064037 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0985. Min Act: -0.0001

Data Index: 481759 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1212571 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0985. Min Act: -0.0001

Data Index: 349916 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0985. Min Act: -0.0001

Data Index: 315607 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1025. Min Act: -0.0001

Data Index: 107787 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0970. Min Act: -0.0001

Data Index: 426343 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0976. Min Act: -0.0001

Data Index: 202387 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1469956 (Python Code)

Max Activating Token Index: 614

Text #16

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0900. Min Act: -0.0001

Data Index: 678094 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1232709 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0900. Min Act: -0.0001

Data Index: 314634 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1003078 (C4 (Web Text))

Max Activating Token Index: 5