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

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

Neuron 3809 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: 0.9694. Min Range: -0.9694

Max Act: 0.9694. Min Act: -0.0001

Data Index: 1563560 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1587435 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9146. Min Act: -0.0001

Data Index: 1375284 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.9015. Min Act: -0.0001

Data Index: 1454012 (Python Code)

Max Activating Token Index: 706

Text #4

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8710. Min Act: -0.0001

Data Index: 1643588 (Python Code)

Max Activating Token Index: 158

Text #5

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8582. Min Act: -0.0001

Data Index: 1556307 (Python Code)

Max Activating Token Index: 542

Text #6

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8513. Min Act: -0.0001

Data Index: 1550653 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1646408 (Python Code)

Max Activating Token Index: 382

Text #8

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7957. Min Act: -0.0001

Data Index: 1413832 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8581. Min Act: -0.0001

Data Index: 1431117 (Python Code)

Max Activating Token Index: 281

Text #10

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7651. Min Act: -0.0001

Data Index: 1496401 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8443. Min Act: -0.0001

Data Index: 1442922 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1490118 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8607. Min Act: -0.0001

Data Index: 1521162 (Python Code)

Max Activating Token Index: 67

Text #14

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8064. Min Act: -0.0001

Data Index: 1441248 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1650459 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1438250 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8020. Min Act: -0.0001

Data Index: 1596251 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1467287 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8053. Min Act: -0.0001

Data Index: 1469524 (Python Code)

Max Activating Token Index: 51