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

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

Neuron 4124 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7810. Min Act: -0.0002

Data Index: 1500889 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7603. Min Act: -0.0002

Data Index: 1417421 (Python Code)

Max Activating Token Index: 876

Text #2

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7525. Min Act: -0.0002

Data Index: 1474649 (Python Code)

Max Activating Token Index: 479

Text #3

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7736. Min Act: -0.0002

Data Index: 1399840 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7104. Min Act: -0.0002

Data Index: 1512745 (Python Code)

Max Activating Token Index: 351

Text #5

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7254. Min Act: -0.0002

Data Index: 1537637 (Python Code)

Max Activating Token Index: 629

Text #6

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6917. Min Act: -0.0002

Data Index: 1427019 (Python Code)

Max Activating Token Index: 74

Text #7

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6867. Min Act: -0.0002

Data Index: 1615054 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6784. Min Act: -0.0002

Data Index: 1435149 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7427. Min Act: -0.0002

Data Index: 1634113 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7201. Min Act: -0.0002

Data Index: 1465726 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7163. Min Act: -0.0002

Data Index: 1500019 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6887. Min Act: -0.0002

Data Index: 1600488 (Python Code)

Max Activating Token Index: 401

Text #13

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6465. Min Act: -0.0002

Data Index: 1525168 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6847. Min Act: -0.0002

Data Index: 1511797 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6625. Min Act: -0.0002

Data Index: 1464106 (Python Code)

Max Activating Token Index: 124

Text #16

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7215. Min Act: -0.0002

Data Index: 1393106 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7062. Min Act: -0.0002

Data Index: 1588935 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7280. Min Act: -0.0002

Data Index: 1403003 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7002. Min Act: -0.0002

Data Index: 1410632 (Python Code)

Max Activating Token Index: 18