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

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

Neuron 723 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.7184. Min Act: -0.1700

Data Index: 850816 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5932. Min Act: -0.1700

Data Index: 562174 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5776. Min Act: -0.1700

Data Index: 1216438 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.6089. Min Act: -0.1700

Data Index: 1011425 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5932. Min Act: -0.1700

Data Index: 319332 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.6558. Min Act: -0.1700

Data Index: 1033983 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5776. Min Act: -0.1700

Data Index: 281385 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.6558. Min Act: -0.1700

Data Index: 668106 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5619. Min Act: -0.1700

Data Index: 1225955 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5776. Min Act: -0.1700

Data Index: 479404 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5776. Min Act: -0.1700

Data Index: 97348 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5462. Min Act: -0.1700

Data Index: 116665 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5932. Min Act: -0.1700

Data Index: 66334 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5619. Min Act: -0.1700

Data Index: 531259 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5776. Min Act: -0.1700

Data Index: 416581 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.4836. Min Act: -0.1700

Data Index: 188683 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5932. Min Act: -0.1700

Data Index: 55956 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.4992. Min Act: -0.1700

Data Index: 672864 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.4992. Min Act: -0.1700

Data Index: 28364 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 3.7184. Min Range: -3.7184

Max Act: 3.5306. Min Act: -0.1700

Data Index: 86442 (C4 (Web Text))

Max Activating Token Index: 482