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

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

Neuron 54 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.8793. Min Act: -0.1700

Data Index: 432145 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.8480. Min Act: -0.1700

Data Index: 611105 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.6759. Min Act: -0.1700

Data Index: 1183732 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.7229. Min Act: -0.1700

Data Index: 35902 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.6290. Min Act: -0.1700

Data Index: 1280351 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5977. Min Act: -0.1700

Data Index: 600035 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.6290. Min Act: -0.1700

Data Index: 891999 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.6133. Min Act: -0.1700

Data Index: 561684 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.6133. Min Act: -0.1700

Data Index: 1127665 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5820. Min Act: -0.1700

Data Index: 1102985 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5820. Min Act: -0.1700

Data Index: 617049 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5820. Min Act: -0.1700

Data Index: 272459 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5820. Min Act: -0.1700

Data Index: 142478 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5350. Min Act: -0.1700

Data Index: 194612 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5507. Min Act: -0.1700

Data Index: 217050 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5507. Min Act: -0.1700

Data Index: 628931 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5350. Min Act: -0.1700

Data Index: 314741 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5350. Min Act: -0.1700

Data Index: 406580 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5663. Min Act: -0.1700

Data Index: 459904 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 3.8793. Min Range: -3.8793

Max Act: 3.5507. Min Act: -0.1700

Data Index: 96420 (C4 (Web Text))

Max Activating Token Index: 961