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

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

Neuron 118 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: 3.9693. Min Range: -3.9693

Max Act: 3.9380. Min Act: -0.1700

Data Index: 564031 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9693. Min Act: -0.1700

Data Index: 133571 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9537. Min Act: -0.1700

Data Index: 633818 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9380. Min Act: -0.1700

Data Index: 632587 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9224. Min Act: -0.1700

Data Index: 264085 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9224. Min Act: -0.1700

Data Index: 349737 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9068. Min Act: -0.1700

Data Index: 21655 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9224. Min Act: -0.1700

Data Index: 1214893 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9068. Min Act: -0.1700

Data Index: 776315 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9380. Min Act: -0.1700

Data Index: 778745 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9224. Min Act: -0.1700

Data Index: 274194 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8911. Min Act: -0.1700

Data Index: 306075 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9068. Min Act: -0.1700

Data Index: 109939 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9068. Min Act: -0.1700

Data Index: 1266954 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8911. Min Act: -0.1700

Data Index: 864125 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9380. Min Act: -0.1700

Data Index: 1251769 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.9068. Min Act: -0.1700

Data Index: 1012494 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8911. Min Act: -0.1700

Data Index: 1017790 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8755. Min Act: -0.1700

Data Index: 1158247 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 3.9693. Min Range: -3.9693

Max Act: 3.8911. Min Act: -0.1700

Data Index: 390499 (C4 (Web Text))

Max Activating Token Index: 911