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

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

Neuron 1338 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2926. Min Act: -0.0000

Data Index: 745440 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1853. Min Act: -0.0001

Data Index: 49670 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2221. Min Act: -0.0001

Data Index: 756074 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2222. Min Act: -0.0001

Data Index: 601042 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2010. Min Act: -0.0000

Data Index: 309522 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1314178 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2065. Min Act: -0.0000

Data Index: 33922 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1992. Min Act: -0.0001

Data Index: 860287 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2027. Min Act: -0.0001

Data Index: 675839 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1813. Min Act: -0.0001

Data Index: 1144064 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1720. Min Act: -0.0001

Data Index: 885409 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1161289 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1792. Min Act: -0.0001

Data Index: 347754 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1125174 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1839. Min Act: -0.0000

Data Index: 704390 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1548. Min Act: -0.0001

Data Index: 918110 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1201025 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1113225 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1813. Min Act: -0.0001

Data Index: 382398 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1001735 (C4 (Web Text))

Max Activating Token Index: 491