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

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

Neuron 303 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.9447. Min Act: -0.1700

Data Index: 471430 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.9447. Min Act: -0.1700

Data Index: 595276 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.9134. Min Act: -0.1700

Data Index: 668333 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.8509. Min Act: -0.1700

Data Index: 1271380 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.8509. Min Act: -0.1700

Data Index: 417059 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.8509. Min Act: -0.1700

Data Index: 1056215 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 912341 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.8196. Min Act: -0.1700

Data Index: 1214155 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 313833 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7570. Min Act: -0.1700

Data Index: 1252518 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 676848 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.8196. Min Act: -0.1700

Data Index: 38969 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 811140 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 839753 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 1206490 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.8196. Min Act: -0.1700

Data Index: 1204506 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 644733 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7570. Min Act: -0.1700

Data Index: 653496 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7883. Min Act: -0.1700

Data Index: 1133495 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 3.9447. Min Range: -3.9447

Max Act: 3.7570. Min Act: -0.1700

Data Index: 1316167 (C4 (Web Text))

Max Activating Token Index: 82