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

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

Neuron 5557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1024. Min Range: -1.1024

Max Act: 1.1024. Min Act: -0.0002

Data Index: 1262947 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.9530. Min Act: -0.0002

Data Index: 486131 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8677. Min Act: -0.0002

Data Index: 319351 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.9023. Min Act: -0.0002

Data Index: 311284 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8904. Min Act: -0.0002

Data Index: 170846 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8404. Min Act: -0.0002

Data Index: 1270102 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8451. Min Act: -0.0002

Data Index: 168529 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8674. Min Act: -0.0002

Data Index: 279945 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8617. Min Act: -0.0002

Data Index: 15724 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8519. Min Act: -0.0002

Data Index: 384593 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8725. Min Act: -0.0002

Data Index: 1380639 (Python Code)

Max Activating Token Index: 709

Text #11

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7705. Min Act: -0.0002

Data Index: 1584529 (Python Code)

Max Activating Token Index: 791

Text #12

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7926. Min Act: -0.0002

Data Index: 492545 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7416. Min Act: -0.0002

Data Index: 1267820 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.8026. Min Act: -0.0002

Data Index: 612514 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7763. Min Act: -0.0002

Data Index: 1072390 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7519. Min Act: -0.0002

Data Index: 655068 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7657. Min Act: -0.0002

Data Index: 634256 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7481. Min Act: -0.0002

Data Index: 684753 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 1.1024. Min Range: -1.1024

Max Act: 0.7505. Min Act: -0.0002

Data Index: 977042 (C4 (Web Text))

Max Activating Token Index: 521