Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 648 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.5744. Min Act: -0.1698

Data Index: 1316529 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.5700. Min Act: -0.1696

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.5207. Min Act: -0.1699

Data Index: 284279 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.5183. Min Act: -0.1700

Data Index: 410417 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.4815. Min Act: -0.1699

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.4733. Min Act: -0.1700

Data Index: 961130 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.4032. Min Act: -0.1700

Data Index: 868637 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.4102. Min Act: -0.1696

Data Index: 933401 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3994. Min Act: -0.1697

Data Index: 695703 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3902. Min Act: -0.1700

Data Index: 27329 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3850. Min Act: -0.1700

Data Index: 809958 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3600. Min Act: -0.1700

Data Index: 397700 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3715. Min Act: -0.1700

Data Index: 206376 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3645. Min Act: -0.1692

Data Index: 528262 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3532. Min Act: -0.1699

Data Index: 1255105 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3505. Min Act: -0.1700

Data Index: 146712 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3527. Min Act: -0.1700

Data Index: 809453 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3543. Min Act: -0.1628

Data Index: 1322539 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3616. Min Act: -0.1700

Data Index: 598707 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 3.5744. Min Range: -3.5744

Max Act: 3.3254. Min Act: -0.1700

Data Index: 680051 (C4 (Web Text))

Max Activating Token Index: 716