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

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

Neuron 1934 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.1401. Min Range: -9.1401

Max Act: 9.1401. Min Act: -0.1700

Data Index: 543038 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 9.1401. Min Range: -9.1401

Max Act: 8.2651. Min Act: -0.1690

Data Index: 611675 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 9.1401. Min Range: -9.1401

Max Act: 8.2651. Min Act: -0.1599

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 9.1401. Min Range: -9.1401

Max Act: 8.2026. Min Act: -0.1700

Data Index: 45430 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 9.1401. Min Range: -9.1401

Max Act: 8.2026. Min Act: -0.1700

Data Index: 607441 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.9526. Min Act: -0.1577

Data Index: 493417 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.9214. Min Act: -0.1699

Data Index: 880314 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.8589. Min Act: -0.1696

Data Index: 329755 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.8276. Min Act: -0.1344

Data Index: 458340 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.7964. Min Act: -0.1700

Data Index: 120134 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.7026. Min Act: -0.1699

Data Index: 1046262 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.5151. Min Act: -0.1700

Data Index: 114795 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.5776. Min Act: -0.1693

Data Index: 19096 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.3901. Min Act: -0.1700

Data Index: 525056 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.6089. Min Act: -0.1700

Data Index: 345540 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.3276. Min Act: -0.1700

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.3589. Min Act: -0.1700

Data Index: 100347 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.3901. Min Act: -0.1698

Data Index: 809261 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.3276. Min Act: -0.1700

Data Index: 725519 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 9.1401. Min Range: -9.1401

Max Act: 7.2651. Min Act: -0.1700

Data Index: 585158 (C4 (Web Text))

Max Activating Token Index: 681