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

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

Neuron 4730 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2594. Min Act: -0.0000

Data Index: 240582 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1052402 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2211. Min Act: -0.0000

Data Index: 670323 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1152109 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2100. Min Act: -0.0000

Data Index: 634447 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1181061 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1239324 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1909. Min Act: -0.0000

Data Index: 905739 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1892. Min Act: -0.0000

Data Index: 123226 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1884. Min Act: -0.0000

Data Index: 286783 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1848. Min Act: -0.0000

Data Index: 801174 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1956. Min Act: -0.0000

Data Index: 26094 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1158486 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1918. Min Act: -0.0000

Data Index: 311403 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1077600 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.2037. Min Act: -0.0000

Data Index: 511576 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1898. Min Act: -0.0000

Data Index: 849248 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1812. Min Act: -0.0000

Data Index: 840036 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1763. Min Act: -0.0000

Data Index: 832927 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.2594. Min Range: -0.2594

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1277054 (C4 (Web Text))

Max Activating Token Index: 50