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

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

Neuron 3898 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: 0.2576. Min Range: -0.2576

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1432635 (Python Code)

Max Activating Token Index: 635

Text #1

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1563791 (Python Code)

Max Activating Token Index: 223

Text #2

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1622253 (Python Code)

Max Activating Token Index: 196

Text #3

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1526501 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2576. Min Act: -0.0001

Data Index: 497784 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2063. Min Act: -0.0001

Data Index: 92252 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1966. Min Act: -0.0001

Data Index: 722365 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1627207 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1393269 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2087. Min Act: -0.0000

Data Index: 616574 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1414140 (Python Code)

Max Activating Token Index: 485

Text #11

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1616894 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1425596 (Python Code)

Max Activating Token Index: 143

Text #13

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2169. Min Act: -0.0000

Data Index: 680623 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2066. Min Act: -0.0000

Data Index: 487671 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1265272 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1899. Min Act: -0.0000

Data Index: 540444 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1917. Min Act: -0.0000

Data Index: 1505099 (Python Code)

Max Activating Token Index: 69

Text #18

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1464482 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 0.2576. Min Range: -0.2576

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1654441 (Python Code)

Max Activating Token Index: 88