Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2062 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1423149 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1655643 (Python Code)

Max Activating Token Index: 813

Text #2

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1550318 (Python Code)

Max Activating Token Index: 537

Text #3

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1462775 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1523804 (Python Code)

Max Activating Token Index: 407

Text #5

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1475893 (Python Code)

Max Activating Token Index: 792

Text #6

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1484672 (Python Code)

Max Activating Token Index: 922

Text #7

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1649173 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1594087 (Python Code)

Max Activating Token Index: 905

Text #9

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1373632 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1614783 (Python Code)

Max Activating Token Index: 629

Text #11

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1589544 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1380950 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1363258 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1479483 (Python Code)

Max Activating Token Index: 742

Text #15

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1586733 (Python Code)

Max Activating Token Index: 739

Text #16

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1537934 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1399134 (Python Code)

Max Activating Token Index: 463

Text #18

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1653336 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 0.1463. Min Range: -0.1463

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1430604 (Python Code)

Max Activating Token Index: 707