Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2016 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7552. Min Act: -0.1700

Data Index: 163296 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7552. Min Act: -0.1700

Data Index: 1146292 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7865. Min Act: -0.1700

Data Index: 483417 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7239. Min Act: -0.1699

Data Index: 840632 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.7239. Min Act: -0.1700

Data Index: 1120033 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6926. Min Act: -0.1700

Data Index: 180770 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5987. Min Act: -0.1700

Data Index: 532320 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.6613. Min Act: -0.1700

Data Index: 224659 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5987. Min Act: -0.1700

Data Index: 1234576 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5987. Min Act: -0.1700

Data Index: 175019 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5987. Min Act: -0.1700

Data Index: 701004 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5987. Min Act: -0.1700

Data Index: 75202 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5674. Min Act: -0.1700

Data Index: 881364 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5674. Min Act: -0.1700

Data Index: 51492 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5674. Min Act: -0.1700

Data Index: 141576 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5987. Min Act: -0.1700

Data Index: 945354 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5361. Min Act: -0.1700

Data Index: 1022663 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5674. Min Act: -0.1700

Data Index: 853677 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5361. Min Act: -0.1700

Data Index: 602171 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 3.7865. Min Range: -3.7865

Max Act: 3.5674. Min Act: -0.1700

Data Index: 421865 (C4 (Web Text))

Max Activating Token Index: 455