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

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

Neuron 2794 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: 4.5823. Min Range: -4.5823

Max Act: 4.5823. Min Act: -0.0000

Data Index: 1398599 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.9553. Min Act: -0.0000

Data Index: 1533239 (Python Code)

Max Activating Token Index: 799

Text #2

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.6732. Min Act: -0.0000

Data Index: 1451554 (Python Code)

Max Activating Token Index: 526

Text #3

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.3484. Min Act: -0.0000

Data Index: 1510591 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.4994. Min Act: -0.0000

Data Index: 1616709 (Python Code)

Max Activating Token Index: 195

Text #5

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.2643. Min Act: -0.0000

Data Index: 1651733 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.5355. Min Act: -0.0000

Data Index: 1490598 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.2284. Min Act: -0.0000

Data Index: 1480070 (Python Code)

Max Activating Token Index: 49

Text #8

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.2189. Min Act: -0.0000

Data Index: 1448473 (Python Code)

Max Activating Token Index: 153

Text #9

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.1780. Min Act: -0.0000

Data Index: 1566620 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.1628. Min Act: -0.0000

Data Index: 1502954 (Python Code)

Max Activating Token Index: 92

Text #11

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.0792. Min Act: -0.0000

Data Index: 1497826 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.0473. Min Act: -0.0000

Data Index: 1615524 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.1878. Min Act: -0.0000

Data Index: 1400208 (Python Code)

Max Activating Token Index: 983

Text #14

Max Range: 4.5823. Min Range: -4.5823

Max Act: 2.8879. Min Act: -0.0000

Data Index: 1647064 (Python Code)

Max Activating Token Index: 696

Text #15

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.2908. Min Act: -0.0000

Data Index: 1529581 (Python Code)

Max Activating Token Index: 149

Text #16

Max Range: 4.5823. Min Range: -4.5823

Max Act: 2.9580. Min Act: -0.0000

Data Index: 1465985 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 4.5823. Min Range: -4.5823

Max Act: 3.0963. Min Act: -0.0000

Data Index: 1538815 (Python Code)

Max Activating Token Index: 894

Text #18

Max Range: 4.5823. Min Range: -4.5823

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1378629 (Python Code)

Max Activating Token Index: 251

Text #19

Max Range: 4.5823. Min Range: -4.5823

Max Act: 2.6630. Min Act: -0.0000

Data Index: 1457565 (Python Code)

Max Activating Token Index: 270