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

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

Neuron 1645 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2310. Min Act: -0.0001

Data Index: 623108 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2172. Min Act: -0.0001

Data Index: 935732 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2166. Min Act: -0.0001

Data Index: 741617 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2116. Min Act: -0.0001

Data Index: 749851 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1957. Min Act: -0.0001

Data Index: 810666 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1945. Min Act: -0.0001

Data Index: 177699 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1061371 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1119248 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1860. Min Act: -0.0001

Data Index: 38725 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1053611 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1716. Min Act: -0.0001

Data Index: 1058976 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1103378 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1719. Min Act: -0.0001

Data Index: 37626 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1725. Min Act: -0.0001

Data Index: 466054 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1822. Min Act: -0.0000

Data Index: 970858 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1794. Min Act: -0.0001

Data Index: 205841 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1724. Min Act: -0.0001

Data Index: 274166 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1695. Min Act: -0.0001

Data Index: 727421 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1715. Min Act: -0.0001

Data Index: 50725 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1615. Min Act: -0.0001

Data Index: 92637 (C4 (Web Text))

Max Activating Token Index: 378