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

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

Neuron 3570 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: 3.6787. Min Range: -3.6787

Max Act: 3.6787. Min Act: -0.0001

Data Index: 1486237 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.9609. Min Act: -0.0001

Data Index: 1555935 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.9202. Min Act: -0.0001

Data Index: 1653536 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7113. Min Act: -0.0001

Data Index: 1542431 (Python Code)

Max Activating Token Index: 564

Text #4

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1499724 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7799. Min Act: -0.0001

Data Index: 1645116 (Python Code)

Max Activating Token Index: 919

Text #6

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7553. Min Act: -0.0001

Data Index: 1596800 (Python Code)

Max Activating Token Index: 51

Text #7

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7525. Min Act: -0.0000

Data Index: 1593113 (Python Code)

Max Activating Token Index: 670

Text #8

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.6128. Min Act: -0.0000

Data Index: 1424732 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.8620. Min Act: -0.0000

Data Index: 1640699 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.4834. Min Act: -0.0001

Data Index: 1507583 (Python Code)

Max Activating Token Index: 648

Text #11

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7254. Min Act: -0.0000

Data Index: 1473285 (Python Code)

Max Activating Token Index: 624

Text #12

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7153. Min Act: -0.0000

Data Index: 1421387 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.8813. Min Act: -0.0000

Data Index: 1640088 (Python Code)

Max Activating Token Index: 85

Text #14

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7074. Min Act: -0.0000

Data Index: 1523024 (Python Code)

Max Activating Token Index: 666

Text #15

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.7134. Min Act: -0.0000

Data Index: 1493847 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.6942. Min Act: -0.0001

Data Index: 1397089 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.6921. Min Act: -0.0001

Data Index: 1409821 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.5649. Min Act: -0.0000

Data Index: 1525574 (Python Code)

Max Activating Token Index: 371

Text #19

Max Range: 3.6787. Min Range: -3.6787

Max Act: 2.9325. Min Act: -0.0000

Data Index: 1599134 (Python Code)

Max Activating Token Index: 711