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

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

Neuron 1529 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: 3.9647. Min Range: -3.9647

Max Act: 3.9647. Min Act: -0.1700

Data Index: 156655 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8865. Min Act: -0.1700

Data Index: 122502 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.9022. Min Act: -0.1700

Data Index: 842823 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8865. Min Act: -0.1700

Data Index: 1296488 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8396. Min Act: -0.1700

Data Index: 48570 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7927. Min Act: -0.1700

Data Index: 156617 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8709. Min Act: -0.1700

Data Index: 332578 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.9022. Min Act: -0.1700

Data Index: 807738 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8240. Min Act: -0.1700

Data Index: 527847 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8240. Min Act: -0.1700

Data Index: 740984 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8396. Min Act: -0.1700

Data Index: 1159012 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7927. Min Act: -0.1700

Data Index: 785907 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.8553. Min Act: -0.1700

Data Index: 1303537 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7771. Min Act: -0.1700

Data Index: 1032570 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7458. Min Act: -0.1700

Data Index: 879813 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7301. Min Act: -0.1700

Data Index: 75916 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7927. Min Act: -0.1700

Data Index: 1000303 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7145. Min Act: -0.1700

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7614. Min Act: -0.1700

Data Index: 288418 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.9647. Min Range: -3.9647

Max Act: 3.7614. Min Act: -0.1700

Data Index: 967964 (C4 (Web Text))

Max Activating Token Index: 467