Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2488 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0003

Data Index: 584967 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0710. Min Act: -0.0002

Data Index: 996014 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0682. Min Act: -0.0003

Data Index: 353008 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0669. Min Act: -0.0003

Data Index: 297594 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0586. Min Act: -0.0003

Data Index: 1219414 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1342340 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1196448 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0552. Min Act: -0.0003

Data Index: 717137 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0544. Min Act: -0.0003

Data Index: 556714 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1049738 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0524. Min Act: -0.0003

Data Index: 704933 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0543. Min Act: -0.0003

Data Index: 281174 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1411653 (Python Code)

Max Activating Token Index: 442

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0519. Min Act: -0.0003

Data Index: 621147 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0511. Min Act: -0.0002

Data Index: 464222 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1508945 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0499. Min Act: -0.0002

Data Index: 744444 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1533729 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0515. Min Act: -0.0003

Data Index: 950661 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1586371 (Python Code)

Max Activating Token Index: 398