Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 596 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.3065. Min Act: -0.1700

Data Index: 571282 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.3378. Min Act: -0.1700

Data Index: 262526 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.3378. Min Act: -0.1700

Data Index: 967834 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.2753. Min Act: -0.1700

Data Index: 348807 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.2753. Min Act: -0.1700

Data Index: 566215 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.2440. Min Act: -0.1700

Data Index: 1099902 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.2753. Min Act: -0.1700

Data Index: 1044831 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.2128. Min Act: -0.1700

Data Index: 1257826 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1815. Min Act: -0.1700

Data Index: 74396 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1815. Min Act: -0.1700

Data Index: 643381 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1815. Min Act: -0.1700

Data Index: 619390 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1503. Min Act: -0.1700

Data Index: 214412 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1815. Min Act: -0.1700

Data Index: 1355217 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1815. Min Act: -0.1700

Data Index: 817407 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1815. Min Act: -0.1700

Data Index: 487570 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.0878. Min Act: -0.1700

Data Index: 929264 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1503. Min Act: -0.1700

Data Index: 385752 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.1503. Min Act: -0.1700

Data Index: 679004 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.0878. Min Act: -0.1700

Data Index: 865926 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 5.3378. Min Range: -5.3378

Max Act: 5.0878. Min Act: -0.1700

Data Index: 886571 (C4 (Web Text))

Max Activating Token Index: 1008