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

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

Neuron 1674 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: 3.2534. Min Range: -3.2534

Max Act: 3.2534. Min Act: -0.1700

Data Index: 654775 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.2063. Min Act: -0.1700

Data Index: 1032303 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1748. Min Act: -0.1700

Data Index: 1293297 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1590. Min Act: -0.1700

Data Index: 1165595 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1433. Min Act: -0.1700

Data Index: 803016 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1905. Min Act: -0.1700

Data Index: 26824 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1275. Min Act: -0.1700

Data Index: 364286 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1433. Min Act: -0.1700

Data Index: 556790 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1118. Min Act: -0.1700

Data Index: 574784 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1433. Min Act: -0.1700

Data Index: 653654 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0960. Min Act: -0.1700

Data Index: 986760 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0960. Min Act: -0.1700

Data Index: 835964 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.1118. Min Act: -0.1700

Data Index: 337152 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0802. Min Act: -0.1700

Data Index: 269488 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0802. Min Act: -0.1700

Data Index: 739898 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0960. Min Act: -0.1700

Data Index: 1226211 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0645. Min Act: -0.1700

Data Index: 179445 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0802. Min Act: -0.1700

Data Index: 279787 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0802. Min Act: -0.1700

Data Index: 151534 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.2534. Min Range: -3.2534

Max Act: 3.0487. Min Act: -0.1700

Data Index: 753322 (C4 (Web Text))

Max Activating Token Index: 328