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

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

Neuron 2651 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.0602. Min Act: -0.0000

Data Index: 1442559 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.6903. Min Act: -0.0000

Data Index: 1586017 (Python Code)

Max Activating Token Index: 429

Text #2

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.4324. Min Act: -0.0000

Data Index: 1536987 (Python Code)

Max Activating Token Index: 595

Text #3

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.5529. Min Act: -0.0000

Data Index: 1546875 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.3194. Min Act: -0.0000

Data Index: 1515035 (Python Code)

Max Activating Token Index: 952

Text #5

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.3583. Min Act: -0.0000

Data Index: 1578710 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.4585. Min Act: -0.0000

Data Index: 1438923 (Python Code)

Max Activating Token Index: 174

Text #7

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.3144. Min Act: -0.0000

Data Index: 1537878 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.4434. Min Act: -0.0000

Data Index: 1407224 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.3883. Min Act: -0.0000

Data Index: 1603519 (Python Code)

Max Activating Token Index: 528

Text #10

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.2513. Min Act: -0.0000

Data Index: 1603635 (Python Code)

Max Activating Token Index: 334

Text #11

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.3250. Min Act: -0.0000

Data Index: 1454531 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.5507. Min Act: -0.0000

Data Index: 1604853 (Python Code)

Max Activating Token Index: 792

Text #13

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.2923. Min Act: -0.0000

Data Index: 1533815 (Python Code)

Max Activating Token Index: 246

Text #14

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.2840. Min Act: -0.0000

Data Index: 1571217 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.3721. Min Act: -0.0000

Data Index: 1403251 (Python Code)

Max Activating Token Index: 850

Text #16

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.2094. Min Act: -0.0000

Data Index: 1649133 (Python Code)

Max Activating Token Index: 699

Text #17

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.0142. Min Act: -0.0000

Data Index: 998492 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1396195 (Python Code)

Max Activating Token Index: 256

Text #19

Max Range: 2.6903. Min Range: -2.6903

Max Act: 2.1961. Min Act: -0.0000

Data Index: 1485964 (Python Code)

Max Activating Token Index: 87