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

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

Neuron 1075 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0776. Min Range: -1.0776

Max Act: 1.0776. Min Act: -0.0000

Data Index: 208385 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9192. Min Act: -0.0000

Data Index: 179224 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1138924 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.7405. Min Act: -0.0000

Data Index: 715893 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.6550. Min Act: -0.0000

Data Index: 675644 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.6368. Min Act: -0.0000

Data Index: 468026 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.6055. Min Act: -0.0000

Data Index: 605644 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5902. Min Act: -0.0000

Data Index: 844570 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5724. Min Act: -0.0000

Data Index: 506195 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.6051. Min Act: -0.0000

Data Index: 742120 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1229988 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5930. Min Act: -0.0000

Data Index: 507292 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1302692 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5870. Min Act: -0.0001

Data Index: 1228120 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5629. Min Act: -0.0000

Data Index: 775520 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5988. Min Act: -0.0000

Data Index: 976631 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5788. Min Act: -0.0000

Data Index: 865501 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5770. Min Act: -0.0000

Data Index: 898874 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5542. Min Act: -0.0000

Data Index: 183132 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.5689. Min Act: -0.0000

Data Index: 661095 (C4 (Web Text))

Max Activating Token Index: 258