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

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

Neuron 3857 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1827. Min Range: -6.1827

Max Act: 6.1622. Min Act: -0.0000

Data Index: 899719 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 6.1827. Min Range: -6.1827

Max Act: 6.0877. Min Act: -0.0000

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 6.1827. Min Range: -6.1827

Max Act: 6.0245. Min Act: -0.0000

Data Index: 1079308 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 6.1827. Min Range: -6.1827

Max Act: 6.1701. Min Act: -0.0000

Data Index: 747708 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.9851. Min Act: -0.0000

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.9853. Min Act: -0.0001

Data Index: 196843 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 6.1827. Min Range: -6.1827

Max Act: 6.1827. Min Act: -0.0001

Data Index: 1032363 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.8591. Min Act: -0.0000

Data Index: 456199 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 6.1827. Min Range: -6.1827

Max Act: 6.0287. Min Act: -0.0000

Data Index: 1078393 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 6.1827. Min Range: -6.1827

Max Act: 6.1481. Min Act: -0.0000

Data Index: 1234992 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.8645. Min Act: -0.0000

Data Index: 855979 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.8567. Min Act: -0.0001

Data Index: 1140838 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.8528. Min Act: -0.0000

Data Index: 1191066 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.8306. Min Act: -0.0001

Data Index: 1006005 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.8588. Min Act: -0.0001

Data Index: 858294 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.6369. Min Act: -0.0000

Data Index: 553376 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.6306. Min Act: -0.0000

Data Index: 145620 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.8191. Min Act: -0.0001

Data Index: 1308863 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.6119. Min Act: -0.0000

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 6.1827. Min Range: -6.1827

Max Act: 5.7647. Min Act: -0.0000

Data Index: 40650 (C4 (Web Text))

Max Activating Token Index: 89