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

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

Neuron 45 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: 4.1765. Min Range: -4.1765

Max Act: 4.1765. Min Act: -0.1700

Data Index: 1589431 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 4.1765. Min Range: -4.1765

Max Act: 4.0515. Min Act: -0.1700

Data Index: 1439688 (Python Code)

Max Activating Token Index: 544

Text #2

Max Range: 4.1765. Min Range: -4.1765

Max Act: 4.0202. Min Act: -0.1700

Data Index: 1566955 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 4.1765. Min Range: -4.1765

Max Act: 4.0202. Min Act: -0.1700

Data Index: 1424406 (Python Code)

Max Activating Token Index: 364

Text #4

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9890. Min Act: -0.1700

Data Index: 755780 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9890. Min Act: -0.1700

Data Index: 1574191 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9577. Min Act: -0.1700

Data Index: 1583810 (Python Code)

Max Activating Token Index: 605

Text #7

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9890. Min Act: -0.1700

Data Index: 1544678 (Python Code)

Max Activating Token Index: 463

Text #8

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9264. Min Act: -0.1700

Data Index: 1380308 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9890. Min Act: -0.1700

Data Index: 1625999 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1589969 (Python Code)

Max Activating Token Index: 269

Text #11

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9264. Min Act: -0.1700

Data Index: 403956 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1424409 (Python Code)

Max Activating Token Index: 180

Text #13

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1563018 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1480100 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.9108. Min Act: -0.1700

Data Index: 1604462 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8482. Min Act: -0.1700

Data Index: 1383103 (Python Code)

Max Activating Token Index: 408

Text #17

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8482. Min Act: -0.1700

Data Index: 1599980 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8795. Min Act: -0.1700

Data Index: 1566370 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 4.1765. Min Range: -4.1765

Max Act: 3.8795. Min Act: -0.1700

Data Index: 1506551 (Python Code)

Max Activating Token Index: 984