Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1756 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5696. Min Act: -0.0001

Data Index: 1175777 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5485. Min Act: -0.0001

Data Index: 41538 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5370. Min Act: -0.0001

Data Index: 907153 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5299. Min Act: -0.0001

Data Index: 314255 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5239. Min Act: -0.0001

Data Index: 739284 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4994. Min Act: -0.0001

Data Index: 536715 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4987. Min Act: -0.0001

Data Index: 1101637 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4759. Min Act: -0.0001

Data Index: 740930 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4797. Min Act: -0.0001

Data Index: 1169919 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4943. Min Act: -0.0001

Data Index: 67360 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1025341 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4928. Min Act: -0.0001

Data Index: 709834 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5041. Min Act: -0.0001

Data Index: 844064 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4840. Min Act: -0.0001

Data Index: 1140232 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4853. Min Act: -0.0001

Data Index: 541379 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4585. Min Act: -0.0001

Data Index: 832674 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4717. Min Act: -0.0001

Data Index: 594688 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4696. Min Act: -0.0001

Data Index: 833738 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4673. Min Act: -0.0001

Data Index: 1141746 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4673. Min Act: -0.0001

Data Index: 358644 (C4 (Web Text))

Max Activating Token Index: 17