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

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

Neuron 1341 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0059. Min Range: -4.0059

Max Act: 4.0059. Min Act: -0.1700

Data Index: 22300 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.9747. Min Act: -0.1700

Data Index: 840898 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.9121. Min Act: -0.1700

Data Index: 114122 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.7870. Min Act: -0.1700

Data Index: 379670 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.7870. Min Act: -0.1700

Data Index: 223831 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.7557. Min Act: -0.1700

Data Index: 509143 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.7557. Min Act: -0.1700

Data Index: 1194808 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.7244. Min Act: -0.1700

Data Index: 1352304 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.6618. Min Act: -0.1700

Data Index: 199020 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.6618. Min Act: -0.1700

Data Index: 49696 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.6305. Min Act: -0.1700

Data Index: 543192 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.5992. Min Act: -0.1700

Data Index: 463099 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.6305. Min Act: -0.1700

Data Index: 1201787 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.6618. Min Act: -0.1700

Data Index: 633956 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.6618. Min Act: -0.1700

Data Index: 781516 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.5992. Min Act: -0.1700

Data Index: 940900 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.5992. Min Act: -0.1700

Data Index: 114001 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.5992. Min Act: -0.1700

Data Index: 1065861 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.5992. Min Act: -0.1700

Data Index: 1140302 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 4.0059. Min Range: -4.0059

Max Act: 3.5992. Min Act: -0.1700

Data Index: 617940 (C4 (Web Text))

Max Activating Token Index: 19