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

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

Neuron 1020 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: 3.4420. Min Range: -3.4420

Max Act: 3.4420. Min Act: -0.1700

Data Index: 1023283 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.3938. Min Act: -0.1699

Data Index: 627506 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.2770. Min Act: -0.1689

Data Index: 1196407 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.2820. Min Act: -0.1700

Data Index: 398320 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.2307. Min Act: -0.1671

Data Index: 959445 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.1789. Min Act: -0.1698

Data Index: 324222 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.1424. Min Act: -0.1698

Data Index: 770817 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.1287. Min Act: -0.1700

Data Index: 192278 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.1289. Min Act: -0.1695

Data Index: 978484 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.1277. Min Act: -0.1699

Data Index: 673136 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0974. Min Act: -0.1700

Data Index: 1200623 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0950. Min Act: -0.1699

Data Index: 1532464 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0764. Min Act: -0.1678

Data Index: 1097728 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0765. Min Act: -0.1700

Data Index: 371593 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0800. Min Act: -0.1700

Data Index: 638392 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0707. Min Act: -0.1700

Data Index: 848911 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0569. Min Act: -0.1699

Data Index: 78011 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0552. Min Act: -0.1698

Data Index: 880196 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0591. Min Act: -0.1692

Data Index: 707984 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 3.4420. Min Range: -3.4420

Max Act: 3.0490. Min Act: -0.1700

Data Index: 887902 (C4 (Web Text))

Max Activating Token Index: 635