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

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

Neuron 816 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.1648. Min Act: -0.1700

Data Index: 516560 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0860. Min Act: -0.1700

Data Index: 207797 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0545. Min Act: -0.1700

Data Index: 859427 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0545. Min Act: -0.1700

Data Index: 770752 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0229. Min Act: -0.1700

Data Index: 176829 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0229. Min Act: -0.1700

Data Index: 998229 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0229. Min Act: -0.1700

Data Index: 9212 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0071. Min Act: -0.1700

Data Index: 334160 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0071. Min Act: -0.1700

Data Index: 784567 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9754. Min Act: -0.1700

Data Index: 453335 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9913. Min Act: -0.1700

Data Index: 866559 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 3.1648. Min Range: -3.1648

Max Act: 3.0071. Min Act: -0.1700

Data Index: 1300303 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9438. Min Act: -0.1700

Data Index: 539787 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9279. Min Act: -0.1700

Data Index: 892116 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9279. Min Act: -0.1700

Data Index: 1163943 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9279. Min Act: -0.1700

Data Index: 409283 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9279. Min Act: -0.1700

Data Index: 36767 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.9279. Min Act: -0.1700

Data Index: 105561 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.8645. Min Act: -0.1700

Data Index: 316048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.1648. Min Range: -3.1648

Max Act: 2.8168. Min Act: -0.1700

Data Index: 874057 (C4 (Web Text))

Max Activating Token Index: 154