Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1603 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0482. Min Range: -5.0482

Max Act: 5.0482. Min Act: -0.1700

Data Index: 375081 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 5.0482. Min Range: -5.0482

Max Act: 5.0169. Min Act: -0.1700

Data Index: 576833 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.9232. Min Act: -0.1700

Data Index: 140443 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.8607. Min Act: -0.1700

Data Index: 886477 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.8919. Min Act: -0.1700

Data Index: 515634 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.8607. Min Act: -0.1700

Data Index: 1215430 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.8294. Min Act: -0.1700

Data Index: 633944 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.6732. Min Act: -0.1700

Data Index: 132079 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.6419. Min Act: -0.1700

Data Index: 16674 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.6107. Min Act: -0.1700

Data Index: 632234 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.6107. Min Act: -0.1700

Data Index: 967260 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.6419. Min Act: -0.1700

Data Index: 331370 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5794. Min Act: -0.1700

Data Index: 1613149 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5481. Min Act: -0.1699

Data Index: 419794 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5794. Min Act: -0.1700

Data Index: 131837 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5169. Min Act: -0.1700

Data Index: 282043 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5169. Min Act: -0.1700

Data Index: 457754 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5794. Min Act: -0.1700

Data Index: 857713 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5481. Min Act: -0.1700

Data Index: 495553 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 5.0482. Min Range: -5.0482

Max Act: 4.5794. Min Act: -0.1700

Data Index: 371310 (C4 (Web Text))

Max Activating Token Index: 1019