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

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

Neuron 1355 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.5806. Min Act: -0.1700

Data Index: 1314736 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.5493. Min Act: -0.1700

Data Index: 174910 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.5493. Min Act: -0.1700

Data Index: 570028 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.5023. Min Act: -0.1700

Data Index: 807044 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.5023. Min Act: -0.1700

Data Index: 388263 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4866. Min Act: -0.1700

Data Index: 1534272 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4866. Min Act: -0.1700

Data Index: 332679 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4866. Min Act: -0.1700

Data Index: 1007385 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4553. Min Act: -0.1700

Data Index: 37373 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4710. Min Act: -0.1700

Data Index: 1095171 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4553. Min Act: -0.1700

Data Index: 734083 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4710. Min Act: -0.1700

Data Index: 783377 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4710. Min Act: -0.1700

Data Index: 1084010 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4396. Min Act: -0.1700

Data Index: 250871 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4710. Min Act: -0.1700

Data Index: 1292129 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4553. Min Act: -0.1700

Data Index: 1095241 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4396. Min Act: -0.1700

Data Index: 846723 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4553. Min Act: -0.1700

Data Index: 533291 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4710. Min Act: -0.1700

Data Index: 169408 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 3.5806. Min Range: -3.5806

Max Act: 3.4396. Min Act: -0.1700

Data Index: 1272713 (C4 (Web Text))

Max Activating Token Index: 306