Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 267 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2346. Min Act: -0.0001

Data Index: 524584 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2160. Min Act: -0.0001

Data Index: 651542 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2039. Min Act: -0.0001

Data Index: 936511 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2034. Min Act: -0.0001

Data Index: 255700 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1956. Min Act: -0.0001

Data Index: 287396 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2139. Min Act: -0.0001

Data Index: 303187 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2062. Min Act: -0.0001

Data Index: 1345704 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1977. Min Act: -0.0001

Data Index: 667177 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1976. Min Act: -0.0001

Data Index: 171036 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2083. Min Act: -0.0001

Data Index: 790744 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2016. Min Act: -0.0001

Data Index: 986351 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1984. Min Act: -0.0001

Data Index: 762349 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1957. Min Act: -0.0001

Data Index: 325701 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1096732 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1047915 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1180601 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1768. Min Act: -0.0001

Data Index: 515221 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1870. Min Act: -0.0001

Data Index: 401708 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1886. Min Act: -0.0001

Data Index: 1270724 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1056087 (C4 (Web Text))

Max Activating Token Index: 553