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

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

Neuron 635 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: 3.8707. Min Range: -3.8707

Max Act: 3.8707. Min Act: -0.1700

Data Index: 1648377 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7925. Min Act: -0.1700

Data Index: 1491478 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7612. Min Act: -0.1700

Data Index: 1370317 (Python Code)

Max Activating Token Index: 276

Text #3

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7769. Min Act: -0.1700

Data Index: 1598660 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.7456. Min Act: -0.1694

Data Index: 1398779 (Python Code)

Max Activating Token Index: 219

Text #5

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6673. Min Act: -0.1700

Data Index: 1428590 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6517. Min Act: -0.1700

Data Index: 1422664 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6673. Min Act: -0.1700

Data Index: 1374427 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6360. Min Act: -0.1700

Data Index: 1431112 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6360. Min Act: -0.1700

Data Index: 1588019 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1599973 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6360. Min Act: -0.1698

Data Index: 1377079 (Python Code)

Max Activating Token Index: 517

Text #12

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1417659 (Python Code)

Max Activating Token Index: 274

Text #13

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6360. Min Act: -0.1700

Data Index: 1380585 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6360. Min Act: -0.1688

Data Index: 1361309 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6047. Min Act: -0.1700

Data Index: 1475761 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.6047. Min Act: -0.1700

Data Index: 1505934 (Python Code)

Max Activating Token Index: 537

Text #17

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5734. Min Act: -0.1700

Data Index: 1490381 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5577. Min Act: -0.1699

Data Index: 1411097 (Python Code)

Max Activating Token Index: 821

Text #19

Max Range: 3.8707. Min Range: -3.8707

Max Act: 3.5577. Min Act: -0.1700

Data Index: 1442794 (Python Code)

Max Activating Token Index: 508