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

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

Neuron 2899 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2866. Min Range: -2.2866

Max Act: 2.2866. Min Act: -0.0000

Data Index: 500616 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.9171. Min Act: -0.0000

Data Index: 228201 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.6696. Min Act: -0.0000

Data Index: 1290650 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.6606. Min Act: -0.0000

Data Index: 297984 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.5881. Min Act: -0.0000

Data Index: 536923 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.5790. Min Act: -0.0000

Data Index: 344892 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3824. Min Act: -0.0000

Data Index: 830148 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3525. Min Act: -0.0000

Data Index: 413654 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.4620. Min Act: -0.0000

Data Index: 60725 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3315. Min Act: -0.0000

Data Index: 1101212 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.2729. Min Act: -0.0000

Data Index: 627134 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1229494 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3087. Min Act: -0.0000

Data Index: 974408 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1223092 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.2891. Min Act: -0.0000

Data Index: 856087 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.2982. Min Act: -0.0000

Data Index: 992647 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3410. Min Act: -0.0000

Data Index: 112184 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.3546. Min Act: -0.0000

Data Index: 1050396 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.2671. Min Act: -0.0000

Data Index: 592690 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 2.2866. Min Range: -2.2866

Max Act: 1.1782. Min Act: -0.0000

Data Index: 704486 (C4 (Web Text))

Max Activating Token Index: 491