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

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

Neuron 2595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.7224. Min Act: -0.0000

Data Index: 1417989 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.4355. Min Act: -0.0000

Data Index: 1633519 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.3657. Min Act: -0.0000

Data Index: 1373781 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.5126. Min Act: -0.0000

Data Index: 1643456 (Python Code)

Max Activating Token Index: 373

Text #4

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.1471. Min Act: -0.0000

Data Index: 1002156 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.4788. Min Act: -0.0000

Data Index: 1578489 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.0039. Min Act: -0.0000

Data Index: 330377 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.9845. Min Act: -0.0000

Data Index: 1533469 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.1293. Min Act: -0.0000

Data Index: 1497018 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.0622. Min Act: -0.0000

Data Index: 1450359 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.9245. Min Act: -0.0000

Data Index: 1374285 (Python Code)

Max Activating Token Index: 629

Text #11

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.9094. Min Act: -0.0000

Data Index: 1539148 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.0063. Min Act: -0.0000

Data Index: 1601918 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.6958. Min Act: -0.0000

Data Index: 1642179 (Python Code)

Max Activating Token Index: 102

Text #14

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.1478. Min Act: -0.0000

Data Index: 1511093 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.9331. Min Act: -0.0000

Data Index: 1539147 (Python Code)

Max Activating Token Index: 519

Text #16

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.7853. Min Act: -0.0000

Data Index: 1490484 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 5.7224. Min Range: -5.7224

Max Act: 5.2670. Min Act: -0.0000

Data Index: 1532671 (Python Code)

Max Activating Token Index: 697

Text #18

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.7388. Min Act: -0.0000

Data Index: 1640001 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 5.7224. Min Range: -5.7224

Max Act: 4.6001. Min Act: -0.0000

Data Index: 1623334 (Python Code)

Max Activating Token Index: 757