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

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

Neuron 420 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: 3.1473. Min Range: -3.1473

Max Act: 3.1473. Min Act: -0.1700

Data Index: 626186 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.1316. Min Act: -0.1700

Data Index: 400034 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0212. Min Act: -0.1700

Data Index: 763656 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0212. Min Act: -0.1700

Data Index: 797605 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0212. Min Act: -0.1700

Data Index: 179700 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1449199 (Python Code)

Max Activating Token Index: 51

Text #6

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0053. Min Act: -0.1700

Data Index: 1086617 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0212. Min Act: -0.1700

Data Index: 404393 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1222570 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0053. Min Act: -0.1700

Data Index: 356516 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0053. Min Act: -0.1700

Data Index: 157726 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0053. Min Act: -0.1700

Data Index: 580561 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0053. Min Act: -0.1700

Data Index: 1346895 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 514762 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 566357 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 329394 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 981610 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 3.1473. Min Range: -3.1473

Max Act: 3.0053. Min Act: -0.1700

Data Index: 191251 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1000659 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 3.1473. Min Range: -3.1473

Max Act: 2.9895. Min Act: -0.1700

Data Index: 678052 (C4 (Web Text))

Max Activating Token Index: 798