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

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

Neuron 545 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: 5.3569. Min Range: -5.3569

Max Act: 5.3569. Min Act: -0.1700

Data Index: 1297809 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.2007. Min Act: -0.1700

Data Index: 594173 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.1226. Min Act: -0.1700

Data Index: 923704 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.1226. Min Act: -0.1700

Data Index: 1119660 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.1382. Min Act: -0.1700

Data Index: 1070113 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0288. Min Act: -0.1700

Data Index: 909379 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0757. Min Act: -0.1700

Data Index: 699735 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0601. Min Act: -0.1700

Data Index: 904322 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0132. Min Act: -0.1700

Data Index: 1296647 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0288. Min Act: -0.1700

Data Index: 1220006 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0444. Min Act: -0.1700

Data Index: 431052 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0132. Min Act: -0.1700

Data Index: 1056809 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0132. Min Act: -0.1700

Data Index: 569133 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0288. Min Act: -0.1700

Data Index: 406527 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 5.3569. Min Range: -5.3569

Max Act: 4.9663. Min Act: -0.1700

Data Index: 559007 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 5.3569. Min Range: -5.3569

Max Act: 4.9819. Min Act: -0.1700

Data Index: 649586 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0757. Min Act: -0.1700

Data Index: 948533 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 5.3569. Min Range: -5.3569

Max Act: 4.9976. Min Act: -0.1700

Data Index: 198295 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0444. Min Act: -0.1700

Data Index: 1271870 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 5.3569. Min Range: -5.3569

Max Act: 5.0601. Min Act: -0.1700

Data Index: 371779 (C4 (Web Text))

Max Activating Token Index: 859