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

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

Neuron 3508 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1827. Min Range: -1.1827

Max Act: 1.1827. Min Act: -0.0000

Data Index: 553114 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.9728. Min Act: -0.0000

Data Index: 997344 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.9907. Min Act: -0.0000

Data Index: 447846 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.9865. Min Act: -0.0000

Data Index: 826641 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.9049. Min Act: -0.0000

Data Index: 334881 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1010264 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1335471 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1105330 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.8131. Min Act: -0.0000

Data Index: 118410 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.8087. Min Act: -0.0000

Data Index: 327370 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7967. Min Act: -0.0000

Data Index: 968077 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1045171 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7147. Min Act: -0.0000

Data Index: 906892 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7536. Min Act: 0.0000

Data Index: 1216475 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7643. Min Act: -0.0000

Data Index: 470309 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.6635. Min Act: -0.0000

Data Index: 111764 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1170711 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7510. Min Act: -0.0000

Data Index: 607073 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1166731 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 1.1827. Min Range: -1.1827

Max Act: 0.7466. Min Act: -0.0000

Data Index: 688843 (C4 (Web Text))

Max Activating Token Index: 836