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

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

Neuron 3998 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.1186. Min Act: -0.0000

Data Index: 591695 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0684. Min Act: -0.0000

Data Index: 812799 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0730. Min Act: -0.0000

Data Index: 621486 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1148776 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0060. Min Act: -0.0000

Data Index: 313180 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9349. Min Act: -0.0000

Data Index: 544893 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9766. Min Act: -0.0000

Data Index: 316585 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.1186. Min Range: -1.1186

Max Act: 1.0113. Min Act: -0.0000

Data Index: 273303 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8229. Min Act: -0.0000

Data Index: 969974 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8726. Min Act: -0.0000

Data Index: 544283 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9173. Min Act: -0.0000

Data Index: 853508 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1201740 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.9052. Min Act: -0.0000

Data Index: 717101 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1351275 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8877. Min Act: -0.0000

Data Index: 593571 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.7896. Min Act: -0.0000

Data Index: 406025 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1251550 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8676. Min Act: -0.0000

Data Index: 228711 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1098463 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 1.1186. Min Range: -1.1186

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1060293 (C4 (Web Text))

Max Activating Token Index: 419