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

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

Neuron 1490 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: 3.8012. Min Range: -3.8012

Max Act: 3.8012. Min Act: -0.1700

Data Index: 314094 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.7699. Min Act: -0.1700

Data Index: 708595 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.7699. Min Act: -0.1700

Data Index: 88378 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.7386. Min Act: -0.1700

Data Index: 778748 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.7386. Min Act: -0.1700

Data Index: 240010 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.6448. Min Act: -0.1700

Data Index: 1243390 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.6448. Min Act: -0.1700

Data Index: 445747 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.6448. Min Act: -0.1700

Data Index: 695850 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.6761. Min Act: -0.1700

Data Index: 290227 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.6134. Min Act: -0.1700

Data Index: 579403 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5821. Min Act: -0.1700

Data Index: 905569 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5821. Min Act: -0.1700

Data Index: 590202 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5508. Min Act: -0.1700

Data Index: 1332855 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.6134. Min Act: -0.1700

Data Index: 588879 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5821. Min Act: -0.1700

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5821. Min Act: -0.1700

Data Index: 166991 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.6134. Min Act: -0.1700

Data Index: 134666 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5508. Min Act: -0.1700

Data Index: 1036629 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5821. Min Act: -0.1700

Data Index: 1044210 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 3.8012. Min Range: -3.8012

Max Act: 3.5508. Min Act: -0.1700

Data Index: 931825 (C4 (Web Text))

Max Activating Token Index: 828