Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1202 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: -0.0006

Data Index: 1016964 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0508. Min Act: -0.0006

Data Index: 563892 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0516. Min Act: -0.0006

Data Index: 1017977 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0487. Min Act: -0.0006

Data Index: 228087 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0487. Min Act: -0.0006

Data Index: 796120 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0455. Min Act: -0.0006

Data Index: 360703 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0489. Min Act: -0.0006

Data Index: 1042143 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0511. Min Act: -0.0006

Data Index: 1169663 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0500. Min Act: -0.0006

Data Index: 134830 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0501. Min Act: -0.0006

Data Index: 949732 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0510. Min Act: -0.0006

Data Index: 757636 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0510. Min Act: -0.0006

Data Index: 606200 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0463. Min Act: -0.0006

Data Index: 195689 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0469. Min Act: -0.0006

Data Index: 1586 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0468. Min Act: -0.0006

Data Index: 23151 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0501. Min Act: -0.0006

Data Index: 178451 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0519. Min Act: -0.0006

Data Index: 70860 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1054176 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0472. Min Act: -0.0006

Data Index: 1126826 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0487. Min Act: -0.0006

Data Index: 1328853 (C4 (Web Text))

Max Activating Token Index: 39