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

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

Neuron 527 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.5187. Min Act: -0.1700

Data Index: 1348780 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.5501. Min Act: -0.1700

Data Index: 364625 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.5187. Min Act: -0.1700

Data Index: 569347 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.4874. Min Act: -0.1700

Data Index: 437558 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.5187. Min Act: -0.1700

Data Index: 665251 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.4560. Min Act: -0.1700

Data Index: 1070385 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.4560. Min Act: -0.1700

Data Index: 1042396 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.4560. Min Act: -0.1700

Data Index: 14870 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.3933. Min Act: -0.1700

Data Index: 965223 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.3933. Min Act: -0.1700

Data Index: 1289082 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.3306. Min Act: -0.1700

Data Index: 7293 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.2991. Min Act: -0.1700

Data Index: 841542 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.3619. Min Act: -0.1700

Data Index: 982132 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.3619. Min Act: -0.1700

Data Index: 362393 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.3619. Min Act: -0.1700

Data Index: 1068260 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.2991. Min Act: -0.1700

Data Index: 670004 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.2991. Min Act: -0.1700

Data Index: 804357 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.3619. Min Act: -0.1700

Data Index: 83260 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.2834. Min Act: -0.1700

Data Index: 35203 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 3.5501. Min Range: -3.5501

Max Act: 3.2677. Min Act: -0.1700

Data Index: 364583 (C4 (Web Text))

Max Activating Token Index: 533