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

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

Neuron 49 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: 5.1844. Min Range: -5.1844

Max Act: 5.1531. Min Act: -0.1700

Data Index: 415179 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.1844. Min Act: -0.1700

Data Index: 446639 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.1844. Min Act: -0.1700

Data Index: 14698 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0906. Min Act: -0.1700

Data Index: 282773 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0906. Min Act: -0.1700

Data Index: 1226644 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0594. Min Act: -0.1700

Data Index: 1291356 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0906. Min Act: -0.1700

Data Index: 946108 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0594. Min Act: -0.1700

Data Index: 202909 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0906. Min Act: -0.1700

Data Index: 407400 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0906. Min Act: -0.1700

Data Index: 726354 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0906. Min Act: -0.1700

Data Index: 78393 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0594. Min Act: -0.1700

Data Index: 430654 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9969. Min Act: -0.1700

Data Index: 431354 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0281. Min Act: -0.1700

Data Index: 716370 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0281. Min Act: -0.1700

Data Index: 627572 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 5.1844. Min Range: -5.1844

Max Act: 5.0281. Min Act: -0.1700

Data Index: 939931 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9969. Min Act: -0.1700

Data Index: 618907 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9344. Min Act: -0.1700

Data Index: 1274786 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9656. Min Act: -0.1700

Data Index: 226842 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 5.1844. Min Range: -5.1844

Max Act: 4.9656. Min Act: -0.1700

Data Index: 1265071 (C4 (Web Text))

Max Activating Token Index: 626