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

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

Neuron 356 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: 3.6438. Min Range: -3.6438

Max Act: 3.6438. Min Act: -0.1700

Data Index: 137442 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.5600. Min Act: -0.1700

Data Index: 425572 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.5829. Min Act: -0.1700

Data Index: 111944 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.5642. Min Act: -0.1700

Data Index: 841779 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.5650. Min Act: -0.1700

Data Index: 493603 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.4861. Min Act: -0.1700

Data Index: 405677 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.4340. Min Act: -0.1700

Data Index: 1128221 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.4483. Min Act: -0.1700

Data Index: 497697 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.4253. Min Act: -0.1700

Data Index: 633014 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.4035. Min Act: -0.1698

Data Index: 651299 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3861. Min Act: -0.1700

Data Index: 139622 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3988. Min Act: -0.1700

Data Index: 676948 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.4009. Min Act: -0.1700

Data Index: 1343980 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3899. Min Act: -0.1700

Data Index: 716416 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3725. Min Act: -0.1699

Data Index: 346473 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3578. Min Act: -0.1699

Data Index: 941548 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3616. Min Act: -0.1697

Data Index: 498852 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3690. Min Act: -0.1699

Data Index: 581891 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3555. Min Act: -0.1700

Data Index: 601053 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 3.6438. Min Range: -3.6438

Max Act: 3.3377. Min Act: -0.1699

Data Index: 541662 (C4 (Web Text))

Max Activating Token Index: 659