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

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

Neuron 1590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.7107. Min Act: -0.1700

Data Index: 205352 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.5857. Min Act: -0.1700

Data Index: 887257 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.5857. Min Act: -0.1700

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.5544. Min Act: -0.1700

Data Index: 227429 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.4919. Min Act: -0.1700

Data Index: 601656 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.5232. Min Act: -0.1700

Data Index: 65494 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.4294. Min Act: -0.1699

Data Index: 1098079 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.4919. Min Act: -0.1699

Data Index: 1110238 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.4294. Min Act: -0.1700

Data Index: 896220 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.2419. Min Act: -0.1700

Data Index: 1174299 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.2107. Min Act: -0.1700

Data Index: 614490 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.2107. Min Act: -0.1700

Data Index: 100040 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.2107. Min Act: -0.1700

Data Index: 938280 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.1794. Min Act: -0.1700

Data Index: 576763 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.1794. Min Act: -0.1700

Data Index: 906679 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.2107. Min Act: -0.1700

Data Index: 626554 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.1794. Min Act: -0.1700

Data Index: 244920 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.1794. Min Act: -0.1700

Data Index: 205898 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.1482. Min Act: -0.1700

Data Index: 1193044 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 5.7107. Min Range: -5.7107

Max Act: 5.1482. Min Act: -0.1700

Data Index: 542422 (C4 (Web Text))

Max Activating Token Index: 295