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

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

Neuron 519 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: 3.1860. Min Range: -3.1860

Max Act: 3.1860. Min Act: -0.1700

Data Index: 485063 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.1134. Min Act: -0.1700

Data Index: 272973 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.1118. Min Act: -0.1700

Data Index: 532337 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.1098. Min Act: -0.1700

Data Index: 233176 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.1321. Min Act: -0.1700

Data Index: 893197 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0974. Min Act: -0.1700

Data Index: 384027 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0781. Min Act: -0.1700

Data Index: 1451310 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0798. Min Act: -0.1700

Data Index: 36582 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0513. Min Act: -0.1700

Data Index: 1296319 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0981. Min Act: -0.1700

Data Index: 603595 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0602. Min Act: -0.1700

Data Index: 1355284 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0586. Min Act: -0.1700

Data Index: 313833 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0725. Min Act: -0.1700

Data Index: 119601 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0632. Min Act: -0.1700

Data Index: 373036 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0868. Min Act: -0.1700

Data Index: 1020279 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0618. Min Act: -0.1700

Data Index: 1237914 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0401. Min Act: -0.1700

Data Index: 181449 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0480. Min Act: -0.1700

Data Index: 345588 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0586. Min Act: -0.1700

Data Index: 1373781 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 3.1860. Min Range: -3.1860

Max Act: 3.0245. Min Act: -0.1700

Data Index: 1109772 (C4 (Web Text))

Max Activating Token Index: 836