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

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

Neuron 4634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1067. Min Act: -0.0000

Data Index: 378989 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.1039. Min Act: -0.0000

Data Index: 239830 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1631010 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1313458 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0939. Min Act: -0.0000

Data Index: 473054 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0895. Min Act: -0.0000

Data Index: 697057 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0878. Min Act: -0.0000

Data Index: 20155 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1349551 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1156539 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1219565 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1355265 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0765. Min Act: -0.0000

Data Index: 873549 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0802. Min Act: -0.0000

Data Index: 620900 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0771. Min Act: -0.0000

Data Index: 437472 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1117952 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0788. Min Act: -0.0000

Data Index: 473856 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1269952 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0741. Min Act: -0.0000

Data Index: 964838 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0709. Min Act: -0.0000

Data Index: 465339 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.1067. Min Range: -0.1067

Max Act: 0.0757. Min Act: -0.0000

Data Index: 442016 (C4 (Web Text))

Max Activating Token Index: 505