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

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

Neuron 1797 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: 3.5998. Min Range: -3.5998

Max Act: 3.5998. Min Act: -0.1700

Data Index: 1167181 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.5842. Min Act: -0.1700

Data Index: 1254935 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.4432. Min Act: -0.1700

Data Index: 641968 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.4902. Min Act: -0.1700

Data Index: 1247883 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3804. Min Act: -0.1700

Data Index: 364746 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3490. Min Act: -0.1700

Data Index: 77085 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3804. Min Act: -0.1700

Data Index: 344234 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3490. Min Act: -0.1700

Data Index: 580934 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3334. Min Act: -0.1700

Data Index: 804995 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3334. Min Act: -0.1700

Data Index: 1069810 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3177. Min Act: -0.1700

Data Index: 26157 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.2862. Min Act: -0.1700

Data Index: 817546 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3334. Min Act: -0.1700

Data Index: 945621 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.2862. Min Act: -0.1700

Data Index: 603904 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3334. Min Act: -0.1700

Data Index: 869454 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.2862. Min Act: -0.1700

Data Index: 645500 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3177. Min Act: -0.1700

Data Index: 167117 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.3019. Min Act: -0.1700

Data Index: 1312545 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.2705. Min Act: -0.1700

Data Index: 1211548 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 3.5998. Min Range: -3.5998

Max Act: 3.2705. Min Act: -0.1700

Data Index: 134170 (C4 (Web Text))

Max Activating Token Index: 282