Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1567 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.1761. Min Act: -0.1700

Data Index: 1272793 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0974. Min Act: -0.1700

Data Index: 1141349 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0658. Min Act: -0.1700

Data Index: 1156395 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0658. Min Act: -0.1700

Data Index: 632653 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0500. Min Act: -0.1700

Data Index: 1056840 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0343. Min Act: -0.1700

Data Index: 678506 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0816. Min Act: -0.1700

Data Index: 886606 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0185. Min Act: -0.1700

Data Index: 342598 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0658. Min Act: -0.1700

Data Index: 1348724 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0343. Min Act: -0.1700

Data Index: 568024 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0343. Min Act: -0.1700

Data Index: 22754 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0343. Min Act: -0.1700

Data Index: 159990 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0343. Min Act: -0.1700

Data Index: 879853 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0185. Min Act: -0.1700

Data Index: 60157 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1000559 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0027. Min Act: -0.1700

Data Index: 1349884 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 3.1761. Min Range: -3.1761

Max Act: 2.9552. Min Act: -0.1700

Data Index: 938995 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 3.1761. Min Range: -3.1761

Max Act: 2.9552. Min Act: -0.1700

Data Index: 592037 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 3.1761. Min Range: -3.1761

Max Act: 2.9868. Min Act: -0.1700

Data Index: 334054 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 3.1761. Min Range: -3.1761

Max Act: 3.0027. Min Act: -0.1700

Data Index: 1036221 (C4 (Web Text))

Max Activating Token Index: 342