Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 732 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.5657. Min Act: -0.1700

Data Index: 1381631 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.5814. Min Act: -0.1700

Data Index: 816989 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4874. Min Act: -0.1700

Data Index: 152295 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.5031. Min Act: -0.1700

Data Index: 512923 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4717. Min Act: -0.1700

Data Index: 73981 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4561. Min Act: -0.1700

Data Index: 850929 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.5031. Min Act: -0.1700

Data Index: 1291231 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4404. Min Act: -0.1700

Data Index: 1134795 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4404. Min Act: -0.1700

Data Index: 1238426 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4561. Min Act: -0.1700

Data Index: 1061902 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4717. Min Act: -0.1700

Data Index: 1076359 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.3933. Min Act: -0.1700

Data Index: 1450359 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4090. Min Act: -0.1700

Data Index: 1054736 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4247. Min Act: -0.1700

Data Index: 902388 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4090. Min Act: -0.1700

Data Index: 1109929 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.4090. Min Act: -0.1700

Data Index: 660795 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.3933. Min Act: -0.1700

Data Index: 790641 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.3776. Min Act: -0.1700

Data Index: 771634 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.3776. Min Act: -0.1700

Data Index: 1436695 (Python Code)

Max Activating Token Index: 153

Text #19

Max Range: 3.5814. Min Range: -3.5814

Max Act: 3.3776. Min Act: -0.1700

Data Index: 1515765 (Python Code)

Max Activating Token Index: 386