Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1755 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.3490. Min Act: -0.1700

Data Index: 288855 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.3490. Min Act: -0.1700

Data Index: 1248654 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.3176. Min Act: -0.1700

Data Index: 403348 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.3333. Min Act: -0.1700

Data Index: 407330 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.2391. Min Act: -0.1700

Data Index: 327838 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.2391. Min Act: -0.1700

Data Index: 735841 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.2391. Min Act: -0.1700

Data Index: 586635 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.2076. Min Act: -0.1700

Data Index: 518957 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.2234. Min Act: -0.1700

Data Index: 8655 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1919. Min Act: -0.1700

Data Index: 1331515 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.2076. Min Act: -0.1700

Data Index: 744671 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1919. Min Act: -0.1700

Data Index: 341698 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1919. Min Act: -0.1700

Data Index: 999159 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1919. Min Act: -0.1700

Data Index: 438900 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1762. Min Act: -0.1700

Data Index: 712516 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1604. Min Act: -0.1700

Data Index: 1108037 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1447. Min Act: -0.1700

Data Index: 916876 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1604. Min Act: -0.1700

Data Index: 494689 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1604. Min Act: -0.1700

Data Index: 661918 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 3.3490. Min Range: -3.3490

Max Act: 3.1604. Min Act: -0.1700

Data Index: 420293 (C4 (Web Text))

Max Activating Token Index: 682