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

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

Neuron 5932 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4877. Min Range: -2.4877

Max Act: 2.4877. Min Act: -0.0000

Data Index: 1047740 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 2.4877. Min Range: -2.4877

Max Act: 2.0140. Min Act: -0.0000

Data Index: 520396 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.8121. Min Act: -0.0000

Data Index: 1234766 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.7956. Min Act: -0.0000

Data Index: 1057475 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.7519. Min Act: -0.0000

Data Index: 355425 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.8616. Min Act: -0.0000

Data Index: 420765 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.7390. Min Act: -0.0000

Data Index: 332126 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.7143. Min Act: -0.0000

Data Index: 799051 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.6930. Min Act: -0.0000

Data Index: 806961 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.5950. Min Act: -0.0000

Data Index: 823587 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.6756. Min Act: -0.0000

Data Index: 521987 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1306732 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.6253. Min Act: -0.0000

Data Index: 138063 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.6993. Min Act: -0.0000

Data Index: 110634 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.5888. Min Act: -0.0000

Data Index: 852863 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.5936. Min Act: -0.0000

Data Index: 1265133 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.5317. Min Act: -0.0000

Data Index: 594336 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.5540. Min Act: -0.0000

Data Index: 355296 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.4896. Min Act: -0.0000

Data Index: 788678 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 2.4877. Min Range: -2.4877

Max Act: 1.5446. Min Act: -0.0000

Data Index: 907705 (C4 (Web Text))

Max Activating Token Index: 572