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

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

Neuron 1552 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1092190 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2100. Min Act: -0.0001

Data Index: 8345 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2288. Min Act: -0.0000

Data Index: 35833 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1352342 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2099. Min Act: -0.0001

Data Index: 462000 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2205. Min Act: -0.0001

Data Index: 25748 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1972. Min Act: -0.0000

Data Index: 42480 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1075065 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1059775 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1918. Min Act: -0.0001

Data Index: 403683 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1961. Min Act: -0.0000

Data Index: 755481 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1883. Min Act: -0.0000

Data Index: 233526 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1805. Min Act: -0.0001

Data Index: 923850 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1094971 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1151644 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1669. Min Act: -0.0001

Data Index: 702401 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1060201 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1841. Min Act: -0.0001

Data Index: 128722 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1780. Min Act: -0.0000

Data Index: 55452 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1832. Min Act: -0.0001

Data Index: 976910 (C4 (Web Text))

Max Activating Token Index: 480