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

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

Neuron 5827 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3852. Min Range: -2.3852

Max Act: 2.3852. Min Act: -0.0000

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 2.3852. Min Range: -2.3852

Max Act: 2.1296. Min Act: -0.0000

Data Index: 1635775 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 2.3852. Min Range: -2.3852

Max Act: 2.0817. Min Act: -0.0000

Data Index: 1521759 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.9510. Min Act: -0.0000

Data Index: 1654412 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.9555. Min Act: -0.0000

Data Index: 1369221 (Python Code)

Max Activating Token Index: 911

Text #5

Max Range: 2.3852. Min Range: -2.3852

Max Act: 2.1508. Min Act: -0.0000

Data Index: 1464116 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 2.3852. Min Range: -2.3852

Max Act: 2.0341. Min Act: -0.0000

Data Index: 1078672 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 2.3852. Min Range: -2.3852

Max Act: 2.1377. Min Act: -0.0000

Data Index: 1627627 (Python Code)

Max Activating Token Index: 581

Text #8

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.9472. Min Act: -0.0000

Data Index: 1639386 (Python Code)

Max Activating Token Index: 354

Text #9

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.9848. Min Act: -0.0000

Data Index: 1631640 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.8493. Min Act: -0.0000

Data Index: 1465942 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.8484. Min Act: -0.0000

Data Index: 1641230 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.8056. Min Act: -0.0000

Data Index: 1428750 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.9979. Min Act: -0.0000

Data Index: 1412771 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1382012 (Python Code)

Max Activating Token Index: 454

Text #15

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.8564. Min Act: -0.0000

Data Index: 1655782 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1565633 (Python Code)

Max Activating Token Index: 698

Text #17

Max Range: 2.3852. Min Range: -2.3852

Max Act: 2.0354. Min Act: -0.0000

Data Index: 1565458 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.7981. Min Act: -0.0000

Data Index: 1461286 (Python Code)

Max Activating Token Index: 999

Text #19

Max Range: 2.3852. Min Range: -2.3852

Max Act: 1.7756. Min Act: -0.0000

Data Index: 1445438 (Python Code)

Max Activating Token Index: 353