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

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

Neuron 1552 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: 3.2498. Min Range: -3.2498

Max Act: 3.2340. Min Act: -0.1699

Data Index: 122345 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2498. Min Act: -0.1699

Data Index: 1255087 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2340. Min Act: -0.1696

Data Index: 473281 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2340. Min Act: -0.1699

Data Index: 968394 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2183. Min Act: -0.1695

Data Index: 507488 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2183. Min Act: -0.1688

Data Index: 95855 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2183. Min Act: -0.1699

Data Index: 1109243 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2183. Min Act: -0.1700

Data Index: 970824 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2183. Min Act: -0.1699

Data Index: 754306 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2026. Min Act: -0.1699

Data Index: 414686 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2340. Min Act: -0.1694

Data Index: 457057 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2026. Min Act: -0.1700

Data Index: 926495 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2026. Min Act: -0.1699

Data Index: 670142 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.1869. Min Act: -0.1692

Data Index: 415815 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.1869. Min Act: -0.1697

Data Index: 433927 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.1711. Min Act: -0.1698

Data Index: 876865 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.2026. Min Act: -0.1699

Data Index: 6049 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.1869. Min Act: -0.1700

Data Index: 856429 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.1869. Min Act: -0.1700

Data Index: 478477 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 3.2498. Min Range: -3.2498

Max Act: 3.1869. Min Act: -0.1699

Data Index: 613472 (C4 (Web Text))

Max Activating Token Index: 747