Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 516 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1841. Min Act: -0.1700

Data Index: 1232649 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1998. Min Act: -0.1700

Data Index: 325251 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1684. Min Act: -0.1700

Data Index: 990118 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1526. Min Act: -0.1700

Data Index: 615602 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1526. Min Act: -0.1700

Data Index: 157006 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1369. Min Act: -0.1700

Data Index: 36695 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1526. Min Act: -0.1700

Data Index: 821140 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1211. Min Act: -0.1700

Data Index: 1144766 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1054. Min Act: -0.1700

Data Index: 748064 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1054. Min Act: -0.1700

Data Index: 833900 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0896. Min Act: -0.1700

Data Index: 946235 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0896. Min Act: -0.1700

Data Index: 1171507 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0896. Min Act: -0.1700

Data Index: 579717 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1054. Min Act: -0.1700

Data Index: 99336 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0738. Min Act: -0.1700

Data Index: 27403 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0738. Min Act: -0.1700

Data Index: 549727 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0738. Min Act: -0.1700

Data Index: 418741 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0580. Min Act: -0.1700

Data Index: 100937 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0422. Min Act: -0.1700

Data Index: 215907 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0580. Min Act: -0.1700

Data Index: 58074 (C4 (Web Text))

Max Activating Token Index: 168