Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 86 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0002

Data Index: 300490 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1293185 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0871. Min Act: -0.0002

Data Index: 514543 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0887. Min Act: -0.0002

Data Index: 213630 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0945. Min Act: -0.0002

Data Index: 242773 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0897. Min Act: -0.0002

Data Index: 412754 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0870. Min Act: -0.0002

Data Index: 351780 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0858. Min Act: -0.0002

Data Index: 773680 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0834. Min Act: -0.0002

Data Index: 610656 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0830. Min Act: -0.0002

Data Index: 370775 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0866. Min Act: -0.0002

Data Index: 992373 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0851. Min Act: -0.0002

Data Index: 444251 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0842. Min Act: -0.0002

Data Index: 313831 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0765. Min Act: -0.0002

Data Index: 933756 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0809. Min Act: -0.0002

Data Index: 510485 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1246669 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0872. Min Act: -0.0002

Data Index: 284134 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0844. Min Act: -0.0002

Data Index: 432229 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0831. Min Act: -0.0002

Data Index: 596077 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0815. Min Act: -0.0002

Data Index: 786616 (C4 (Web Text))

Max Activating Token Index: 461