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

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

Neuron 1213 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.9471. Min Act: -0.1700

Data Index: 650118 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.6968. Min Act: -0.1700

Data Index: 1253279 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.7281. Min Act: -0.1700

Data Index: 981558 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.6968. Min Act: -0.1700

Data Index: 1031960 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.6655. Min Act: -0.1700

Data Index: 37573 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.6655. Min Act: -0.1700

Data Index: 1300218 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.6029. Min Act: -0.1700

Data Index: 45600 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5716. Min Act: -0.1700

Data Index: 139172 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5403. Min Act: -0.1700

Data Index: 1023804 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.6029. Min Act: -0.1700

Data Index: 550213 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5716. Min Act: -0.1700

Data Index: 464097 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5403. Min Act: -0.1700

Data Index: 359057 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5716. Min Act: -0.1700

Data Index: 73213 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5716. Min Act: -0.1700

Data Index: 213476 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5403. Min Act: -0.1700

Data Index: 806671 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5716. Min Act: -0.1700

Data Index: 54920 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.6029. Min Act: -0.1700

Data Index: 402452 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5716. Min Act: -0.1700

Data Index: 103219 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.5090. Min Act: -0.1700

Data Index: 1070434 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 3.9471. Min Range: -3.9471

Max Act: 3.4776. Min Act: -0.1700

Data Index: 437164 (C4 (Web Text))

Max Activating Token Index: 767