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

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

Neuron 4061 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: 0.8681. Min Range: -0.8681

Max Act: 0.8681. Min Act: -0.0000

Data Index: 666855 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7762. Min Act: -0.0000

Data Index: 261716 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6460. Min Act: -0.0000

Data Index: 613965 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6429. Min Act: -0.0000

Data Index: 192224 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6834. Min Act: -0.0000

Data Index: 613976 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1476097 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6151. Min Act: -0.0000

Data Index: 630142 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1246675 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5850. Min Act: -0.0000

Data Index: 446440 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6467. Min Act: -0.0000

Data Index: 434568 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5875. Min Act: -0.0000

Data Index: 128241 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5981. Min Act: -0.0000

Data Index: 645082 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5733. Min Act: -0.0000

Data Index: 562947 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1224908 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1035991 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1181653 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5283. Min Act: -0.0000

Data Index: 855196 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1478675 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5807. Min Act: -0.0000

Data Index: 908229 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.4907. Min Act: -0.0000

Data Index: 817269 (C4 (Web Text))

Max Activating Token Index: 874