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

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

Neuron 5587 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0832. Min Range: -1.0832

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1496513 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.9342. Min Act: -0.0001

Data Index: 411940 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1491263 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.9562. Min Act: -0.0001

Data Index: 43914 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1388212 (Python Code)

Max Activating Token Index: 137

Text #5

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8901. Min Act: -0.0001

Data Index: 485573 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1575847 (Python Code)

Max Activating Token Index: 743

Text #7

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8942. Min Act: -0.0000

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1506698 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.7652. Min Act: -0.0000

Data Index: 1465488 (Python Code)

Max Activating Token Index: 691

Text #10

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1436814 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1593460 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1414555 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1490883 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1363675 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1428185 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1647724 (Python Code)

Max Activating Token Index: 563

Text #17

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1481797 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1519892 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 1.0832. Min Range: -1.0832

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1508593 (Python Code)

Max Activating Token Index: 525