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

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

Neuron 1570 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: 3.6501. Min Range: -3.6501

Max Act: 3.6501. Min Act: -0.1700

Data Index: 575756 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.6031. Min Act: -0.1700

Data Index: 825886 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.5718. Min Act: -0.1700

Data Index: 619906 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.5248. Min Act: -0.1700

Data Index: 409503 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.5248. Min Act: -0.1700

Data Index: 1118801 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.5092. Min Act: -0.1700

Data Index: 314772 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.5248. Min Act: -0.1700

Data Index: 1300720 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.5092. Min Act: -0.1700

Data Index: 829595 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4935. Min Act: -0.1700

Data Index: 204795 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4778. Min Act: -0.1700

Data Index: 359001 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4621. Min Act: -0.1700

Data Index: 470602 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4778. Min Act: -0.1700

Data Index: 121645 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4621. Min Act: -0.1700

Data Index: 121936 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4621. Min Act: -0.1700

Data Index: 15168 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4778. Min Act: -0.1700

Data Index: 541192 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4465. Min Act: -0.1700

Data Index: 627628 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4465. Min Act: -0.1700

Data Index: 869714 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4465. Min Act: -0.1700

Data Index: 621583 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4465. Min Act: -0.1700

Data Index: 389128 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 3.6501. Min Range: -3.6501

Max Act: 3.4308. Min Act: -0.1700

Data Index: 996825 (C4 (Web Text))

Max Activating Token Index: 1017