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

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

Neuron 801 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.7850. Min Act: -0.1700

Data Index: 107951 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.7381. Min Act: -0.1700

Data Index: 1305496 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6129. Min Act: -0.1700

Data Index: 599037 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.7068. Min Act: -0.1700

Data Index: 40545 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6911. Min Act: -0.1700

Data Index: 1301950 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6911. Min Act: -0.1700

Data Index: 196163 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6129. Min Act: -0.1700

Data Index: 492100 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6129. Min Act: -0.1700

Data Index: 265023 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5972. Min Act: -0.1700

Data Index: 951532 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6129. Min Act: -0.1700

Data Index: 555459 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6285. Min Act: -0.1700

Data Index: 766016 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.6129. Min Act: -0.1700

Data Index: 811747 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5659. Min Act: -0.1700

Data Index: 258989 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5816. Min Act: -0.1700

Data Index: 1316529 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5816. Min Act: -0.1700

Data Index: 519608 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5659. Min Act: -0.1700

Data Index: 778925 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5503. Min Act: -0.1700

Data Index: 421464 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5816. Min Act: -0.1700

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5503. Min Act: -0.1700

Data Index: 107426 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 3.7850. Min Range: -3.7850

Max Act: 3.5346. Min Act: -0.1700

Data Index: 935638 (C4 (Web Text))

Max Activating Token Index: 678