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

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

Neuron 689 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.5562. Min Act: -0.1700

Data Index: 672522 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.5092. Min Act: -0.1700

Data Index: 775931 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.5092. Min Act: -0.1700

Data Index: 44315 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.4935. Min Act: -0.1700

Data Index: 410443 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3837. Min Act: -0.1700

Data Index: 1080940 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3837. Min Act: -0.1700

Data Index: 985129 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3681. Min Act: -0.1700

Data Index: 150032 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3837. Min Act: -0.1700

Data Index: 191165 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3524. Min Act: -0.1700

Data Index: 532039 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3210. Min Act: -0.1700

Data Index: 791827 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3524. Min Act: -0.1700

Data Index: 565747 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3524. Min Act: -0.1700

Data Index: 32262 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3210. Min Act: -0.1700

Data Index: 509091 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3210. Min Act: -0.1700

Data Index: 629908 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1035062 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3053. Min Act: -0.1700

Data Index: 822423 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.3053. Min Act: -0.1700

Data Index: 1182853 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.2738. Min Act: -0.1700

Data Index: 1129852 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.2738. Min Act: -0.1700

Data Index: 870290 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 3.5562. Min Range: -3.5562

Max Act: 3.2896. Min Act: -0.1700

Data Index: 483227 (C4 (Web Text))

Max Activating Token Index: 10