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

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

Neuron 1775 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: 5.2042. Min Range: -5.2042

Max Act: 5.2042. Min Act: -0.1700

Data Index: 26686 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.1104. Min Act: -0.1700

Data Index: 806407 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0792. Min Act: -0.1700

Data Index: 526146 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0792. Min Act: -0.1700

Data Index: 497662 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0792. Min Act: -0.1700

Data Index: 523720 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0479. Min Act: -0.1700

Data Index: 321592 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0479. Min Act: -0.1700

Data Index: 240917 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0479. Min Act: -0.1700

Data Index: 631815 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0167. Min Act: -0.1700

Data Index: 671182 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0167. Min Act: -0.1700

Data Index: 462956 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0479. Min Act: -0.1700

Data Index: 1237624 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9854. Min Act: -0.1700

Data Index: 893081 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9854. Min Act: -0.1700

Data Index: 199348 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 5.2042. Min Range: -5.2042

Max Act: 5.0167. Min Act: -0.1700

Data Index: 159284 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9229. Min Act: -0.1700

Data Index: 988416 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9542. Min Act: -0.1700

Data Index: 512918 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9542. Min Act: -0.1700

Data Index: 338344 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9542. Min Act: -0.1700

Data Index: 625007 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9542. Min Act: -0.1700

Data Index: 678384 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 5.2042. Min Range: -5.2042

Max Act: 4.9542. Min Act: -0.1700

Data Index: 672457 (C4 (Web Text))

Max Activating Token Index: 821