Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 314 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.7879. Min Act: -0.1700

Data Index: 1336619 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.7606. Min Act: -0.1697

Data Index: 565123 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6833. Min Act: -0.1697

Data Index: 472696 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6830. Min Act: -0.1692

Data Index: 329384 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.7403. Min Act: -0.1694

Data Index: 1090981 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6200. Min Act: -0.1535

Data Index: 605283 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6389. Min Act: -0.1698

Data Index: 191994 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6164. Min Act: -0.1688

Data Index: 554257 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6695. Min Act: -0.1700

Data Index: 405186 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6319. Min Act: -0.1700

Data Index: 670941 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6172. Min Act: -0.1700

Data Index: 235161 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6609. Min Act: -0.1697

Data Index: 773553 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6617. Min Act: -0.1700

Data Index: 350180 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6321. Min Act: -0.1700

Data Index: 525627 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.6422. Min Act: -0.1700

Data Index: 51249 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.5592. Min Act: -0.1700

Data Index: 457093 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.5873. Min Act: -0.1700

Data Index: 320686 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.5601. Min Act: -0.1623

Data Index: 768981 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.5892. Min Act: -0.1700

Data Index: 340901 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 5.7879. Min Range: -5.7879

Max Act: 5.5739. Min Act: -0.1513

Data Index: 1058320 (C4 (Web Text))

Max Activating Token Index: 281