Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3107 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1267. Min Act: -0.0000

Data Index: 944744 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0930. Min Act: -0.0000

Data Index: 399145 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0904. Min Act: -0.0000

Data Index: 490010 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0960. Min Act: 0.0000

Data Index: 373422 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0925. Min Act: -0.0000

Data Index: 131132 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0880. Min Act: -0.0000

Data Index: 297295 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1157996 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1172669 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0863. Min Act: 0.0000

Data Index: 601098 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0871. Min Act: -0.0000

Data Index: 274720 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0832. Min Act: -0.0000

Data Index: 204218 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0863. Min Act: -0.0000

Data Index: 876634 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0761. Min Act: -0.0000

Data Index: 244688 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1171747 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0848. Min Act: -0.0000

Data Index: 276730 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0816. Min Act: -0.0000

Data Index: 789819 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0816. Min Act: -0.0000

Data Index: 277715 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0784. Min Act: 0.0000

Data Index: 1017029 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1098590 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0802. Min Act: -0.0000

Data Index: 490587 (C4 (Web Text))

Max Activating Token Index: 104