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

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

Neuron 829 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7736. Min Range: -2.7736

Max Act: 2.7736. Min Act: -0.0000

Data Index: 541611 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 2.7736. Min Range: -2.7736

Max Act: 2.1284. Min Act: -0.0000

Data Index: 295011 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 2.7736. Min Range: -2.7736

Max Act: 2.0726. Min Act: -0.0000

Data Index: 1133647 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.9507. Min Act: -0.0000

Data Index: 1163252 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.8777. Min Act: -0.0000

Data Index: 222542 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.8755. Min Act: -0.0000

Data Index: 909154 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.8395. Min Act: -0.0000

Data Index: 105898 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.7043. Min Act: -0.0000

Data Index: 155571 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.8935. Min Act: -0.0000

Data Index: 370458 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.7550. Min Act: -0.0000

Data Index: 454774 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.8110. Min Act: -0.0000

Data Index: 948233 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.7037. Min Act: -0.0000

Data Index: 98585 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1111678 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.6744. Min Act: -0.0000

Data Index: 313963 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.5758. Min Act: -0.0000

Data Index: 593266 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.7483. Min Act: -0.0000

Data Index: 541165 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.4715. Min Act: -0.0000

Data Index: 395071 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.6558. Min Act: -0.0000

Data Index: 301703 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.5492. Min Act: -0.0000

Data Index: 505431 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 2.7736. Min Range: -2.7736

Max Act: 1.5387. Min Act: -0.0000

Data Index: 101908 (C4 (Web Text))

Max Activating Token Index: 253