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

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

Neuron 3997 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.2685. Min Act: -0.0000

Data Index: 582732 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1968. Min Act: -0.0000

Data Index: 484021 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1301387 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1503. Min Act: -0.0000

Data Index: 973187 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1424783 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1501. Min Act: -0.0000

Data Index: 676645 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1416. Min Act: -0.0000

Data Index: 164164 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1474408 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1620321 (Python Code)

Max Activating Token Index: 579

Text #9

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1562373 (Python Code)

Max Activating Token Index: 953

Text #10

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1359845 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1633383 (Python Code)

Max Activating Token Index: 882

Text #12

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1078417 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1142. Min Act: -0.0000

Data Index: 895020 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1125919 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1073483 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1061. Min Act: -0.0000

Data Index: 354164 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1216. Min Act: -0.0000

Data Index: 854076 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1515691 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 0.2685. Min Range: -0.2685

Max Act: 0.1069. Min Act: -0.0000

Data Index: 612878 (C4 (Web Text))

Max Activating Token Index: 986