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

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

Neuron 1750 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: 3.9480. Min Range: -3.9480

Max Act: 3.9480. Min Act: -0.1700

Data Index: 425572 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.8386. Min Act: -0.1700

Data Index: 637661 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.7917. Min Act: -0.1700

Data Index: 353654 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.7134. Min Act: -0.1700

Data Index: 1190701 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.7134. Min Act: -0.1700

Data Index: 767310 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6508. Min Act: -0.1700

Data Index: 462842 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6665. Min Act: -0.1700

Data Index: 944279 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6978. Min Act: -0.1700

Data Index: 884840 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6508. Min Act: -0.1700

Data Index: 152214 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6508. Min Act: -0.1700

Data Index: 677883 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6195. Min Act: -0.1700

Data Index: 127690 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6508. Min Act: -0.1700

Data Index: 712638 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6352. Min Act: -0.1700

Data Index: 374437 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6039. Min Act: -0.1700

Data Index: 1218266 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.5882. Min Act: -0.1700

Data Index: 1228910 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6508. Min Act: -0.1700

Data Index: 19973 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6039. Min Act: -0.1700

Data Index: 249810 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6195. Min Act: -0.1700

Data Index: 248017 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.6195. Min Act: -0.1700

Data Index: 1024323 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 3.9480. Min Range: -3.9480

Max Act: 3.5726. Min Act: -0.1700

Data Index: 716907 (C4 (Web Text))

Max Activating Token Index: 525