Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 481 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1521571 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1529189 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1574048 (Python Code)

Max Activating Token Index: 568

Text #3

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1480689 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8767. Min Act: -0.0000

Data Index: 1389387 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1546145 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1481640 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1547771 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1631432 (Python Code)

Max Activating Token Index: 663

Text #9

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1589853 (Python Code)

Max Activating Token Index: 412

Text #10

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1534723 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1560526 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1373773 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1629076 (Python Code)

Max Activating Token Index: 190

Text #14

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1619154 (Python Code)

Max Activating Token Index: 997

Text #15

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1411465 (Python Code)

Max Activating Token Index: 876

Text #16

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1503259 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1656261 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.8030. Min Act: -0.0000

Data Index: 1536103 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 0.9587. Min Range: -0.9587

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1564999 (Python Code)

Max Activating Token Index: 639