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

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

Neuron 1576 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.8463. Min Act: -0.1700

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.7525. Min Act: -0.1700

Data Index: 301300 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.5963. Min Act: -0.1700

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.5650. Min Act: -0.1700

Data Index: 1219392 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.5338. Min Act: -0.1700

Data Index: 807551 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.6275. Min Act: -0.1700

Data Index: 1104540 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.5963. Min Act: -0.1700

Data Index: 170868 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.6275. Min Act: -0.1700

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4713. Min Act: -0.1700

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4713. Min Act: -0.1700

Data Index: 727506 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.5025. Min Act: -0.1700

Data Index: 149515 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4713. Min Act: -0.1700

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4400. Min Act: -0.1700

Data Index: 261456 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4713. Min Act: -0.1700

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.5025. Min Act: -0.1700

Data Index: 104594 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4088. Min Act: -0.1700

Data Index: 1217434 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.3463. Min Act: -0.1700

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.3775. Min Act: -0.1700

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4088. Min Act: -0.1700

Data Index: 319114 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 5.8463. Min Range: -5.8463

Max Act: 5.4088. Min Act: -0.1700

Data Index: 132545 (C4 (Web Text))

Max Activating Token Index: 449