Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5093 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1526666 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1610139 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.9171. Min Act: -0.0000

Data Index: 966109 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1207853 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8589. Min Act: -0.0000

Data Index: 825950 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7886. Min Act: 0.0000

Data Index: 1564017 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1091844 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8095. Min Act: -0.0000

Data Index: 672196 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8251. Min Act: -0.0000

Data Index: 72787 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1347254 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7346. Min Act: -0.0000

Data Index: 87104 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7844. Min Act: -0.0000

Data Index: 736962 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1246976 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7547. Min Act: -0.0000

Data Index: 441944 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7647. Min Act: -0.0000

Data Index: 770374 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7207. Min Act: -0.0000

Data Index: 871446 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1394947 (Python Code)

Max Activating Token Index: 476

Text #17

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1598398 (Python Code)

Max Activating Token Index: 710

Text #18

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1179612 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.9171. Min Range: -0.9171

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1323695 (C4 (Web Text))

Max Activating Token Index: 648