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

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

Neuron 2672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1240493 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2953. Min Act: -0.0000

Data Index: 1411181 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1640615 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2888. Min Act: -0.0000

Data Index: 996855 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1414670 (Python Code)

Max Activating Token Index: 682

Text #5

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1106141 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2624. Min Act: -0.0000

Data Index: 478496 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1166973 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1515047 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2459. Min Act: -0.0000

Data Index: 636645 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1610187 (Python Code)

Max Activating Token Index: 674

Text #11

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.1895. Min Act: -0.0000

Data Index: 980151 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1268944 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1051275 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2019. Min Act: -0.0000

Data Index: 305576 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1119888 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.2147. Min Act: -0.0000

Data Index: 852902 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.1980. Min Act: -0.0000

Data Index: 553345 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1055025 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.3234. Min Range: -0.3234

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1360564 (Python Code)

Max Activating Token Index: 477