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

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

Neuron 1128 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1364. Min Range: -1.1364

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1619844 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 1.1364. Min Range: -1.1364

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1624688 (Python Code)

Max Activating Token Index: 562

Text #2

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1624756 (Python Code)

Max Activating Token Index: 630

Text #3

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1436325 (Python Code)

Max Activating Token Index: 850

Text #4

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1391178 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1375599 (Python Code)

Max Activating Token Index: 711

Text #6

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1409911 (Python Code)

Max Activating Token Index: 890

Text #7

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1622069 (Python Code)

Max Activating Token Index: 692

Text #8

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1363115 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6606. Min Act: -0.0000

Data Index: 80820 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1453005 (Python Code)

Max Activating Token Index: 532

Text #11

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1464623 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1440693 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1518538 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1458893 (Python Code)

Max Activating Token Index: 555

Text #15

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1509162 (Python Code)

Max Activating Token Index: 959

Text #16

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6521. Min Act: -0.0000

Data Index: 1437039 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1398751 (Python Code)

Max Activating Token Index: 972

Text #18

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6884. Min Act: -0.0000

Data Index: 698374 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.1364. Min Range: -1.1364

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1465390 (Python Code)

Max Activating Token Index: 102