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

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

Neuron 1666 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4117. Min Range: -8.4117

Max Act: 8.4117. Min Act: -0.0000

Data Index: 1573600 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 8.4117. Min Range: -8.4117

Max Act: 8.1324. Min Act: -0.0000

Data Index: 1361795 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.8840. Min Act: -0.0000

Data Index: 1534258 (Python Code)

Max Activating Token Index: 982

Text #3

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.8540. Min Act: -0.0000

Data Index: 1619457 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 8.4117. Min Range: -8.4117

Max Act: 8.0269. Min Act: -0.0000

Data Index: 1530120 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 8.4117. Min Range: -8.4117

Max Act: 8.1552. Min Act: -0.0000

Data Index: 1553679 (Python Code)

Max Activating Token Index: 688

Text #6

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.7892. Min Act: -0.0000

Data Index: 1461551 (Python Code)

Max Activating Token Index: 852

Text #7

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.7604. Min Act: -0.0000

Data Index: 1420996 (Python Code)

Max Activating Token Index: 773

Text #8

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.8670. Min Act: -0.0000

Data Index: 1430500 (Python Code)

Max Activating Token Index: 885

Text #9

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.8287. Min Act: -0.0000

Data Index: 1533368 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 8.4117. Min Range: -8.4117

Max Act: 8.3731. Min Act: -0.0000

Data Index: 1447766 (Python Code)

Max Activating Token Index: 973

Text #11

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.5774. Min Act: -0.0000

Data Index: 1427087 (Python Code)

Max Activating Token Index: 883

Text #12

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.9223. Min Act: -0.0000

Data Index: 1610283 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.3917. Min Act: -0.0000

Data Index: 1429698 (Python Code)

Max Activating Token Index: 897

Text #14

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.5896. Min Act: -0.0000

Data Index: 1478026 (Python Code)

Max Activating Token Index: 916

Text #15

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.5488. Min Act: -0.0000

Data Index: 1456231 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.3525. Min Act: -0.0000

Data Index: 1459991 (Python Code)

Max Activating Token Index: 600

Text #17

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.1691. Min Act: -0.0000

Data Index: 1534744 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.4841. Min Act: -0.0000

Data Index: 1424485 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 8.4117. Min Range: -8.4117

Max Act: 7.4115. Min Act: -0.0000

Data Index: 1590620 (Python Code)

Max Activating Token Index: 764