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

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

Neuron 5324 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0002

Data Index: 64570 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1396027 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1120573 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0815. Min Act: -0.0002

Data Index: 319035 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0820. Min Act: -0.0002

Data Index: 302632 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0811. Min Act: -0.0002

Data Index: 517079 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0812. Min Act: -0.0002

Data Index: 875915 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0811. Min Act: -0.0002

Data Index: 734084 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0805. Min Act: -0.0002

Data Index: 39005 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0810. Min Act: -0.0002

Data Index: 300593 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1163812 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0796. Min Act: -0.0002

Data Index: 888514 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0784. Min Act: -0.0002

Data Index: 46221 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1225902 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0794. Min Act: -0.0002

Data Index: 798111 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0798. Min Act: -0.0002

Data Index: 83043 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1440361 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1211727 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0766. Min Act: -0.0002

Data Index: 463937 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0790. Min Act: -0.0002

Data Index: 321561 (C4 (Web Text))

Max Activating Token Index: 197