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

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

Neuron 2014 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.7056. Min Act: -0.1700

Data Index: 190049 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.6743. Min Act: -0.1700

Data Index: 408660 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1326550 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.6743. Min Act: -0.1700

Data Index: 1168192 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.6117. Min Act: -0.1700

Data Index: 528984 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5490. Min Act: -0.1700

Data Index: 738824 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5804. Min Act: -0.1700

Data Index: 1349564 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5804. Min Act: -0.1700

Data Index: 864100 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5804. Min Act: -0.1700

Data Index: 867787 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5804. Min Act: -0.1700

Data Index: 422683 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5177. Min Act: -0.1700

Data Index: 930176 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5490. Min Act: -0.1700

Data Index: 51746 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5177. Min Act: -0.1700

Data Index: 986747 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5177. Min Act: -0.1700

Data Index: 947289 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5177. Min Act: -0.1700

Data Index: 950477 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5177. Min Act: -0.1700

Data Index: 989270 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5177. Min Act: -0.1700

Data Index: 1124413 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.4864. Min Act: -0.1700

Data Index: 153177 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.4864. Min Act: -0.1700

Data Index: 126771 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 3.7056. Min Range: -3.7056

Max Act: 3.5177. Min Act: -0.1700

Data Index: 233184 (C4 (Web Text))

Max Activating Token Index: 16