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

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

Neuron 963 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: 3.8591. Min Range: -3.8591

Max Act: 3.8591. Min Act: -0.1700

Data Index: 615180 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.7653. Min Act: -0.1700

Data Index: 894844 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.7027. Min Act: -0.1700

Data Index: 483929 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.7027. Min Act: -0.1700

Data Index: 704728 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.7340. Min Act: -0.1700

Data Index: 58073 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6714. Min Act: -0.1700

Data Index: 1009641 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6714. Min Act: -0.1700

Data Index: 440100 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6714. Min Act: -0.1700

Data Index: 95543 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6401. Min Act: -0.1700

Data Index: 649486 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6401. Min Act: -0.1700

Data Index: 1264512 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6714. Min Act: -0.1700

Data Index: 195481 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6088. Min Act: -0.1700

Data Index: 349710 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6401. Min Act: -0.1700

Data Index: 1147332 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6401. Min Act: -0.1700

Data Index: 699452 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.5775. Min Act: -0.1700

Data Index: 567607 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6088. Min Act: -0.1700

Data Index: 84821 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.7027. Min Act: -0.1700

Data Index: 141781 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6088. Min Act: -0.1700

Data Index: 323966 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.5775. Min Act: -0.1700

Data Index: 1237520 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 3.8591. Min Range: -3.8591

Max Act: 3.6401. Min Act: -0.1700

Data Index: 616637 (C4 (Web Text))

Max Activating Token Index: 36