Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2501. Min Act: -0.0001

Data Index: 284562 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2383. Min Act: -0.0001

Data Index: 960074 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2419. Min Act: -0.0000

Data Index: 802079 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2113. Min Act: -0.0001

Data Index: 951412 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2361. Min Act: -0.0000

Data Index: 251372 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2095. Min Act: -0.0000

Data Index: 986760 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2166. Min Act: -0.0000

Data Index: 168436 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1220403 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2356. Min Act: -0.0001

Data Index: 53025 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2037. Min Act: -0.0001

Data Index: 799959 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2148. Min Act: -0.0001

Data Index: 245356 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2019. Min Act: -0.0000

Data Index: 935927 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1993. Min Act: -0.0000

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2069. Min Act: -0.0000

Data Index: 388196 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2052. Min Act: -0.0001

Data Index: 219097 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2012. Min Act: -0.0000

Data Index: 784967 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1977. Min Act: -0.0001

Data Index: 566723 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1970. Min Act: -0.0000

Data Index: 376647 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1126197 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.2501. Min Range: -0.2501

Max Act: 0.2020. Min Act: -0.0000

Data Index: 108005 (C4 (Web Text))

Max Activating Token Index: 944