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

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

Neuron 4859 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2801. Min Act: -0.0001

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2339. Min Act: -0.0001

Data Index: 725501 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2143. Min Act: -0.0001

Data Index: 322575 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2260. Min Act: -0.0000

Data Index: 696509 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2311. Min Act: -0.0001

Data Index: 761935 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2073. Min Act: -0.0001

Data Index: 513618 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2002. Min Act: -0.0000

Data Index: 558545 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1973. Min Act: -0.0001

Data Index: 401243 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1972. Min Act: -0.0001

Data Index: 332023 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1306521 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1981. Min Act: -0.0001

Data Index: 235326 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1993. Min Act: -0.0000

Data Index: 793428 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1841. Min Act: -0.0000

Data Index: 311267 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1973. Min Act: -0.0001

Data Index: 605642 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1106631 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.2040. Min Act: -0.0000

Data Index: 729302 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1903. Min Act: -0.0001

Data Index: 773157 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1847. Min Act: -0.0001

Data Index: 611455 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1773. Min Act: -0.0001

Data Index: 365869 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.2801. Min Range: -0.2801

Max Act: 0.1897. Min Act: -0.0001

Data Index: 385226 (C4 (Web Text))

Max Activating Token Index: 732