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

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

Neuron 1615 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: 3.8727. Min Range: -3.8727

Max Act: 3.8727. Min Act: -0.1700

Data Index: 548604 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.6850. Min Act: -0.1700

Data Index: 1157256 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.5128. Min Act: -0.1700

Data Index: 108117 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.4971. Min Act: -0.1700

Data Index: 78472 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.4814. Min Act: -0.1700

Data Index: 1225213 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.4971. Min Act: -0.1700

Data Index: 856720 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.4030. Min Act: -0.1700

Data Index: 105360 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.4501. Min Act: -0.1700

Data Index: 1133601 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3873. Min Act: -0.1700

Data Index: 763661 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.4030. Min Act: -0.1700

Data Index: 672991 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.4187. Min Act: -0.1700

Data Index: 776409 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3403. Min Act: -0.1700

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3403. Min Act: -0.1700

Data Index: 727188 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3560. Min Act: -0.1700

Data Index: 881372 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3089. Min Act: -0.1700

Data Index: 34738 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.2932. Min Act: -0.1700

Data Index: 361988 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3403. Min Act: -0.1700

Data Index: 88772 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3403. Min Act: -0.1700

Data Index: 1079561 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3246. Min Act: -0.1700

Data Index: 878824 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 3.8727. Min Range: -3.8727

Max Act: 3.3717. Min Act: -0.1700

Data Index: 38988 (C4 (Web Text))

Max Activating Token Index: 700