Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1296 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4548. Min Act: -0.0004

Data Index: 1374808 (Python Code)

Max Activating Token Index: 985

Text #1

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4231. Min Act: -0.0004

Data Index: 1518756 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4189. Min Act: -0.0004

Data Index: 1373040 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4486. Min Act: -0.0004

Data Index: 1610558 (Python Code)

Max Activating Token Index: 791

Text #4

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3597. Min Act: -0.0004

Data Index: 1542156 (Python Code)

Max Activating Token Index: 596

Text #5

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4190. Min Act: -0.0004

Data Index: 1570462 (Python Code)

Max Activating Token Index: 592

Text #6

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4047. Min Act: -0.0004

Data Index: 1581432 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4447. Min Act: -0.0004

Data Index: 1366789 (Python Code)

Max Activating Token Index: 918

Text #8

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3882. Min Act: -0.0004

Data Index: 1620735 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4059. Min Act: -0.0004

Data Index: 1617955 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4014. Min Act: -0.0004

Data Index: 1449412 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3923. Min Act: -0.0004

Data Index: 1567091 (Python Code)

Max Activating Token Index: 788

Text #12

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4149. Min Act: -0.0004

Data Index: 1595166 (Python Code)

Max Activating Token Index: 855

Text #13

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3794. Min Act: -0.0004

Data Index: 1539896 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4014. Min Act: -0.0004

Data Index: 1373235 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4013. Min Act: -0.0004

Data Index: 1385190 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3995. Min Act: -0.0004

Data Index: 1402544 (Python Code)

Max Activating Token Index: 713

Text #17

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.4140. Min Act: -0.0004

Data Index: 1615861 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3956. Min Act: -0.0004

Data Index: 1629348 (Python Code)

Max Activating Token Index: 514

Text #19

Max Range: 0.4548. Min Range: -0.4548

Max Act: 0.3966. Min Act: -0.0004

Data Index: 1629911 (Python Code)

Max Activating Token Index: 923