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

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

Neuron 1532 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: 0.2767. Min Range: -0.2767

Max Act: 0.2492. Min Act: -0.0001

Data Index: 263900 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2767. Min Act: -0.0001

Data Index: 479384 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2192. Min Act: -0.0001

Data Index: 333168 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2155. Min Act: -0.0001

Data Index: 654160 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1175324 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1936. Min Act: -0.0001

Data Index: 629539 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1897. Min Act: -0.0001

Data Index: 804320 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1147688 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1995. Min Act: -0.0001

Data Index: 1113856 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1830. Min Act: -0.0001

Data Index: 927864 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1775. Min Act: -0.0001

Data Index: 46828 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1973. Min Act: -0.0001

Data Index: 917910 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1940. Min Act: -0.0001

Data Index: 689828 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1860. Min Act: -0.0001

Data Index: 1131873 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1880. Min Act: -0.0001

Data Index: 326541 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1716. Min Act: -0.0001

Data Index: 1246447 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1036270 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1708. Min Act: -0.0001

Data Index: 607226 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1379981 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1620. Min Act: -0.0001

Data Index: 307459 (C4 (Web Text))

Max Activating Token Index: 301