Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 878 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.8756. Min Act: -0.1700

Data Index: 1527656 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.7975. Min Act: -0.1700

Data Index: 1482431 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.6881. Min Act: -0.1700

Data Index: 1435642 (Python Code)

Max Activating Token Index: 559

Text #3

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.7194. Min Act: -0.1700

Data Index: 1444397 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.7038. Min Act: -0.1700

Data Index: 1633229 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.7194. Min Act: -0.1700

Data Index: 1471772 (Python Code)

Max Activating Token Index: 446

Text #6

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.7038. Min Act: -0.1700

Data Index: 1437723 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.7194. Min Act: -0.1700

Data Index: 1480429 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.7350. Min Act: -0.1700

Data Index: 1416626 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.6256. Min Act: -0.1700

Data Index: 1377529 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.6569. Min Act: -0.1700

Data Index: 1573600 (Python Code)

Max Activating Token Index: 430

Text #11

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.6725. Min Act: -0.1700

Data Index: 1390612 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.6100. Min Act: -0.1700

Data Index: 1498804 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.5944. Min Act: -0.1700

Data Index: 1505626 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.6256. Min Act: -0.1700

Data Index: 1445197 (Python Code)

Max Activating Token Index: 513

Text #15

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.5475. Min Act: -0.1700

Data Index: 1460032 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.5319. Min Act: -0.1700

Data Index: 1521343 (Python Code)

Max Activating Token Index: 241

Text #17

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.5006. Min Act: -0.1700

Data Index: 1514229 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.4850. Min Act: -0.1700

Data Index: 1391847 (Python Code)

Max Activating Token Index: 534

Text #19

Max Range: 7.8756. Min Range: -7.8756

Max Act: 7.5006. Min Act: -0.1700

Data Index: 1390369 (Python Code)

Max Activating Token Index: 776