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

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

Neuron 5481 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: 7.2419. Min Range: -7.2419

Max Act: 7.2419. Min Act: -0.0000

Data Index: 1647663 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 7.2419. Min Range: -7.2419

Max Act: 7.0367. Min Act: -0.0000

Data Index: 1527590 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 7.2419. Min Range: -7.2419

Max Act: 6.5921. Min Act: -0.0000

Data Index: 1432234 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 7.2419. Min Range: -7.2419

Max Act: 5.1053. Min Act: -0.0000

Data Index: 1464590 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 7.2419. Min Range: -7.2419

Max Act: 5.1748. Min Act: -0.0000

Data Index: 1087995 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 7.2419. Min Range: -7.2419

Max Act: 5.1479. Min Act: -0.0000

Data Index: 160913 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.7790. Min Act: -0.0000

Data Index: 1437807 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.9279. Min Act: -0.0000

Data Index: 1391047 (Python Code)

Max Activating Token Index: 640

Text #8

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.7923. Min Act: -0.0000

Data Index: 1438038 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.7703. Min Act: -0.0000

Data Index: 1503918 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.7666. Min Act: -0.0000

Data Index: 1466883 (Python Code)

Max Activating Token Index: 800

Text #11

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.8981. Min Act: -0.0000

Data Index: 1365363 (Python Code)

Max Activating Token Index: 608

Text #12

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.2679. Min Act: -0.0000

Data Index: 1416148 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.5013. Min Act: -0.0000

Data Index: 1603695 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.2553. Min Act: -0.0000

Data Index: 1141705 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.3912. Min Act: -0.0000

Data Index: 1601539 (Python Code)

Max Activating Token Index: 434

Text #16

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.0795. Min Act: -0.0000

Data Index: 705351 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.2370. Min Act: -0.0000

Data Index: 1417539 (Python Code)

Max Activating Token Index: 513

Text #18

Max Range: 7.2419. Min Range: -7.2419

Max Act: 3.8504. Min Act: -0.0000

Data Index: 1030549 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 7.2419. Min Range: -7.2419

Max Act: 4.2156. Min Act: -0.0000

Data Index: 1421643 (Python Code)

Max Activating Token Index: 514