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

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

Neuron 1369 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: 8.8847. Min Range: -8.8847

Max Act: 8.8847. Min Act: -0.1619

Data Index: 523274 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.5097. Min Act: -0.1692

Data Index: 174472 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.2285. Min Act: -0.1699

Data Index: 501320 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.2597. Min Act: -0.1582

Data Index: 1208187 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.1972. Min Act: -0.1699

Data Index: 49289 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.1660. Min Act: -0.1666

Data Index: 151690 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.1347. Min Act: -0.1582

Data Index: 715429 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.0722. Min Act: -0.1633

Data Index: 1231504 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.0722. Min Act: -0.1687

Data Index: 81401 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.0722. Min Act: -0.1633

Data Index: 781901 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.0097. Min Act: -0.1619

Data Index: 519768 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 8.8847. Min Range: -8.8847

Max Act: 8.0410. Min Act: -0.1696

Data Index: 199209 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.9785. Min Act: -0.1697

Data Index: 597653 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.9785. Min Act: -0.1666

Data Index: 24321 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.9160. Min Act: -0.1699

Data Index: 420585 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.9472. Min Act: -0.1700

Data Index: 107859 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.9472. Min Act: -0.1699

Data Index: 507585 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.8847. Min Act: -0.1645

Data Index: 871119 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.8847. Min Act: -0.1633

Data Index: 310032 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 8.8847. Min Range: -8.8847

Max Act: 7.8535. Min Act: -0.1582

Data Index: 580634 (C4 (Web Text))

Max Activating Token Index: 391