Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1761 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.6477. Min Act: -0.1700

Data Index: 1642647 (Python Code)

Max Activating Token Index: 466

Text #1

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.6008. Min Act: -0.1700

Data Index: 1470683 (Python Code)

Max Activating Token Index: 420

Text #2

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.6008. Min Act: -0.1700

Data Index: 590006 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1461614 (Python Code)

Max Activating Token Index: 882

Text #4

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.6008. Min Act: -0.1700

Data Index: 1413008 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1352149 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1556387 (Python Code)

Max Activating Token Index: 870

Text #7

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1406789 (Python Code)

Max Activating Token Index: 573

Text #8

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1415101 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5851. Min Act: -0.1700

Data Index: 1377300 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1439762 (Python Code)

Max Activating Token Index: 737

Text #11

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5538. Min Act: -0.1700

Data Index: 1610283 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5851. Min Act: -0.1700

Data Index: 1369500 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1435708 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1443973 (Python Code)

Max Activating Token Index: 1015

Text #15

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1569239 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1556489 (Python Code)

Max Activating Token Index: 689

Text #17

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5381. Min Act: -0.1700

Data Index: 1360020 (Python Code)

Max Activating Token Index: 363

Text #18

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5225. Min Act: -0.1700

Data Index: 1562178 (Python Code)

Max Activating Token Index: 513

Text #19

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5538. Min Act: -0.1700

Data Index: 1559633 (Python Code)

Max Activating Token Index: 818