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

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

Neuron 420 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1388378 (Python Code)

Max Activating Token Index: 506

Text #1

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.3080. Min Act: -0.0000

Data Index: 176503 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2918. Min Act: -0.0000

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2881. Min Act: -0.0000

Data Index: 205974 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2891. Min Act: -0.0000

Data Index: 870275 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2821. Min Act: -0.0000

Data Index: 640001 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2793. Min Act: -0.0000

Data Index: 218766 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2891. Min Act: -0.0000

Data Index: 575620 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2607. Min Act: -0.0000

Data Index: 57979 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1305813 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1005730 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2755. Min Act: -0.0000

Data Index: 620829 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1133458 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1112712 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2686. Min Act: -0.0000

Data Index: 25001 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2484. Min Act: -0.0000

Data Index: 17142 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2816. Min Act: -0.0000

Data Index: 670700 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2598. Min Act: -0.0000

Data Index: 750259 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1355669 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.3945. Min Range: -0.3945

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1143546 (C4 (Web Text))

Max Activating Token Index: 430