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

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

Neuron 1407 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: 3.9887. Min Range: -3.9887

Max Act: 3.9887. Min Act: -0.1700

Data Index: 620319 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.9731. Min Act: -0.1700

Data Index: 364958 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.8636. Min Act: -0.1700

Data Index: 420547 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.8167. Min Act: -0.1700

Data Index: 31960 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.8011. Min Act: -0.1700

Data Index: 593833 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7698. Min Act: -0.1700

Data Index: 556271 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7541. Min Act: -0.1700

Data Index: 781698 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7854. Min Act: -0.1700

Data Index: 1124344 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7854. Min Act: -0.1700

Data Index: 391607 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7541. Min Act: -0.1700

Data Index: 1254838 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7228. Min Act: -0.1700

Data Index: 259175 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7228. Min Act: -0.1700

Data Index: 1076735 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.7228. Min Act: -0.1700

Data Index: 1188505 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.6915. Min Act: -0.1700

Data Index: 90873 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.6759. Min Act: -0.1700

Data Index: 182754 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.6446. Min Act: -0.1700

Data Index: 745181 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.6602. Min Act: -0.1700

Data Index: 988482 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.6446. Min Act: -0.1698

Data Index: 821960 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.6133. Min Act: -0.1700

Data Index: 79100 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 3.9887. Min Range: -3.9887

Max Act: 3.6602. Min Act: -0.1700

Data Index: 877658 (C4 (Web Text))

Max Activating Token Index: 68