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

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

Neuron 2863 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: 0.3166. Min Range: -0.3166

Max Act: 0.3166. Min Act: -0.0000

Data Index: 874617 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2805. Min Act: -0.0000

Data Index: 802895 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1237870 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2563. Min Act: 0.0000

Data Index: 1175028 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2391. Min Act: -0.0000

Data Index: 685697 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2530. Min Act: -0.0000

Data Index: 907110 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2327. Min Act: -0.0000

Data Index: 19890 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2376. Min Act: -0.0000

Data Index: 283915 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2338. Min Act: 0.0000

Data Index: 707072 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2326. Min Act: -0.0000

Data Index: 312993 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1303763 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1248399 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2106. Min Act: -0.0000

Data Index: 45329 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2182. Min Act: -0.0000

Data Index: 128459 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.1877. Min Act: -0.0000

Data Index: 395374 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2061. Min Act: -0.0000

Data Index: 124621 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.1925. Min Act: -0.0000

Data Index: 769332 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2106. Min Act: -0.0000

Data Index: 294432 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2027. Min Act: -0.0000

Data Index: 881781 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.1957. Min Act: -0.0000

Data Index: 504909 (C4 (Web Text))

Max Activating Token Index: 831