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

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

Neuron 939 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1398447 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1598512 (Python Code)

Max Activating Token Index: 132

Text #2

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1576306 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2059. Min Act: -0.0001

Data Index: 1419029 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1627841 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1641648 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1574909 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1649069 (Python Code)

Max Activating Token Index: 1010

Text #8

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1946. Min Act: -0.0001

Data Index: 1615208 (Python Code)

Max Activating Token Index: 982

Text #9

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1442614 (Python Code)

Max Activating Token Index: 338

Text #10

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1627410 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1479366 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1608314 (Python Code)

Max Activating Token Index: 641

Text #13

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1608410 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1393792 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1537289 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1632698 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1496524 (Python Code)

Max Activating Token Index: 253

Text #18

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1653882 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1565546 (Python Code)

Max Activating Token Index: 84