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

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

Neuron 729 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: 3.7378. Min Range: -3.7378

Max Act: 3.7378. Min Act: -0.1700

Data Index: 766245 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.7378. Min Act: -0.1700

Data Index: 1193740 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6908. Min Act: -0.1700

Data Index: 1288564 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6908. Min Act: -0.1700

Data Index: 373670 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6595. Min Act: -0.1700

Data Index: 431117 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6595. Min Act: -0.1700

Data Index: 484444 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6595. Min Act: -0.1700

Data Index: 1030862 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6595. Min Act: -0.1700

Data Index: 661196 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1074712 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6439. Min Act: -0.1700

Data Index: 333553 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6126. Min Act: -0.1700

Data Index: 996804 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1119750 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6126. Min Act: -0.1700

Data Index: 936526 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.6282. Min Act: -0.1700

Data Index: 1289471 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1015246 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.5656. Min Act: -0.1700

Data Index: 217370 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.5499. Min Act: -0.1700

Data Index: 869238 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.5499. Min Act: -0.1700

Data Index: 1650146 (Python Code)

Max Activating Token Index: 357

Text #18

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.5343. Min Act: -0.1700

Data Index: 654602 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 3.7378. Min Range: -3.7378

Max Act: 3.5656. Min Act: -0.1700

Data Index: 1243022 (C4 (Web Text))

Max Activating Token Index: 827