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

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

Neuron 1176 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0804. Min Range: -3.0804

Max Act: 3.0804. Min Act: -0.0000

Data Index: 1504205 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 3.0804. Min Range: -3.0804

Max Act: 3.0139. Min Act: -0.0000

Data Index: 1366801 (Python Code)

Max Activating Token Index: 687

Text #2

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.9059. Min Act: -0.0000

Data Index: 1460871 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.8671. Min Act: -0.0000

Data Index: 1332826 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.6220. Min Act: -0.0000

Data Index: 1585701 (Python Code)

Max Activating Token Index: 831

Text #5

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.8272. Min Act: -0.0000

Data Index: 1519699 (Python Code)

Max Activating Token Index: 313

Text #6

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.7309. Min Act: -0.0000

Data Index: 1448343 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.5526. Min Act: -0.0000

Data Index: 1595955 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.5806. Min Act: -0.0000

Data Index: 1572902 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.5255. Min Act: -0.0000

Data Index: 1595941 (Python Code)

Max Activating Token Index: 256

Text #10

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.4571. Min Act: -0.0000

Data Index: 1542083 (Python Code)

Max Activating Token Index: 791

Text #11

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.4332. Min Act: -0.0000

Data Index: 1603536 (Python Code)

Max Activating Token Index: 775

Text #12

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.2931. Min Act: -0.0000

Data Index: 1448489 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1454344 (Python Code)

Max Activating Token Index: 475

Text #14

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.0062. Min Act: -0.0000

Data Index: 1455983 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.0968. Min Act: -0.0000

Data Index: 1392696 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 3.0804. Min Range: -3.0804

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1564616 (Python Code)

Max Activating Token Index: 1000

Text #17

Max Range: 3.0804. Min Range: -3.0804

Max Act: 1.9629. Min Act: -0.0000

Data Index: 1638690 (Python Code)

Max Activating Token Index: 488

Text #18

Max Range: 3.0804. Min Range: -3.0804

Max Act: 1.9673. Min Act: -0.0000

Data Index: 1375577 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 3.0804. Min Range: -3.0804

Max Act: 1.9583. Min Act: -0.0000

Data Index: 862435 (C4 (Web Text))

Max Activating Token Index: 161