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

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

Neuron 2256 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.7090. Min Act: -0.0001

Data Index: 1385925 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.7111. Min Act: -0.0001

Data Index: 1609363 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6816. Min Act: -0.0001

Data Index: 1444164 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6902. Min Act: -0.0001

Data Index: 1590585 (Python Code)

Max Activating Token Index: 60

Text #4

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6938. Min Act: -0.0001

Data Index: 1518860 (Python Code)

Max Activating Token Index: 533

Text #5

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6806. Min Act: -0.0001

Data Index: 1366339 (Python Code)

Max Activating Token Index: 816

Text #6

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5667. Min Act: -0.0001

Data Index: 1448623 (Python Code)

Max Activating Token Index: 334

Text #7

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6492. Min Act: -0.0001

Data Index: 1499887 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6076. Min Act: -0.0001

Data Index: 1452370 (Python Code)

Max Activating Token Index: 772

Text #9

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1591456 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6606. Min Act: -0.0001

Data Index: 1582929 (Python Code)

Max Activating Token Index: 998

Text #11

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6557. Min Act: -0.0001

Data Index: 1462571 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6442. Min Act: -0.0001

Data Index: 1425073 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6562. Min Act: -0.0001

Data Index: 1575625 (Python Code)

Max Activating Token Index: 652

Text #14

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6430. Min Act: -0.0001

Data Index: 1562360 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.5879. Min Act: -0.0001

Data Index: 1616768 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6105. Min Act: -0.0001

Data Index: 1483126 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1642064 (Python Code)

Max Activating Token Index: 767

Text #18

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6464. Min Act: -0.0001

Data Index: 1361379 (Python Code)

Max Activating Token Index: 932

Text #19

Max Range: 0.7111. Min Range: -0.7111

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1464552 (Python Code)

Max Activating Token Index: 838