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

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

Neuron 1974 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.9875. Min Act: -0.1700

Data Index: 765525 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7998. Min Act: -0.1700

Data Index: 506239 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7686. Min Act: -0.1700

Data Index: 930850 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7686. Min Act: -0.1700

Data Index: 1234740 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7373. Min Act: -0.1700

Data Index: 1306727 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7686. Min Act: -0.1700

Data Index: 530772 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7686. Min Act: -0.1700

Data Index: 731473 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 986562 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7373. Min Act: -0.1700

Data Index: 1233733 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 900227 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 1342973 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7373. Min Act: -0.1700

Data Index: 1150164 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7373. Min Act: -0.1700

Data Index: 581832 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7373. Min Act: -0.1700

Data Index: 414949 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7373. Min Act: -0.1700

Data Index: 1290853 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 1204101 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 98621 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 603493 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 1206014 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7060. Min Act: -0.1700

Data Index: 234612 (C4 (Web Text))

Max Activating Token Index: 973