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

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

Neuron 1848 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1591824 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1585773 (Python Code)

Max Activating Token Index: 400

Text #2

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1602106 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1639932 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1429593 (Python Code)

Max Activating Token Index: 264

Text #5

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1615117 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1566831 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1644452 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1511478 (Python Code)

Max Activating Token Index: 654

Text #9

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1410314 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1456203 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1560076 (Python Code)

Max Activating Token Index: 292

Text #12

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1504143 (Python Code)

Max Activating Token Index: 887

Text #13

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1438862 (Python Code)

Max Activating Token Index: 908

Text #14

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1495974 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1404152 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1571512 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1487549 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1425439 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 0.1050. Min Range: -0.1050

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1654261 (Python Code)

Max Activating Token Index: 363