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

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

Neuron 2792 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: 0.2155. Min Range: -0.2155

Max Act: 0.2155. Min Act: -0.0001

Data Index: 794600 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.2046. Min Act: -0.0001

Data Index: 754100 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1969. Min Act: -0.0001

Data Index: 750606 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1851. Min Act: -0.0001

Data Index: 365467 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1897. Min Act: -0.0001

Data Index: 1119535 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1042939 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1827. Min Act: -0.0001

Data Index: 910931 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1785. Min Act: -0.0001

Data Index: 152686 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1657. Min Act: -0.0001

Data Index: 158893 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1143476 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1685. Min Act: -0.0001

Data Index: 243936 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1328475 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1298446 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1645. Min Act: -0.0001

Data Index: 844211 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1614. Min Act: -0.0001

Data Index: 341348 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1626. Min Act: -0.0001

Data Index: 401786 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1262512 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1564. Min Act: -0.0001

Data Index: 615403 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1080027 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.2155. Min Range: -0.2155

Max Act: 0.1582. Min Act: -0.0001

Data Index: 770784 (C4 (Web Text))

Max Activating Token Index: 71