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

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

Neuron 4263 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: 0.2843. Min Range: -0.2843

Max Act: 0.2843. Min Act: -0.0000

Data Index: 811425 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2276. Min Act: -0.0000

Data Index: 771515 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2252. Min Act: -0.0000

Data Index: 458787 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2253. Min Act: -0.0001

Data Index: 898499 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1344149 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2048. Min Act: -0.0001

Data Index: 549571 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2247. Min Act: -0.0001

Data Index: 599182 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1313212 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2113. Min Act: -0.0001

Data Index: 862745 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1962. Min Act: -0.0001

Data Index: 637499 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2106. Min Act: -0.0001

Data Index: 679819 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1006648 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1923. Min Act: -0.0000

Data Index: 953625 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1952. Min Act: -0.0000

Data Index: 612139 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1965. Min Act: -0.0001

Data Index: 665034 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1886. Min Act: -0.0001

Data Index: 833616 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1790. Min Act: -0.0001

Data Index: 918186 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1996. Min Act: -0.0000

Data Index: 703543 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1959. Min Act: -0.0000

Data Index: 117605 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.2843. Min Range: -0.2843

Max Act: 0.1976. Min Act: -0.0000

Data Index: 299094 (C4 (Web Text))

Max Activating Token Index: 554