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

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

Neuron 770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.9612. Min Act: -0.1700

Data Index: 1180319 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.8674. Min Act: -0.1700

Data Index: 477481 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.8049. Min Act: -0.1700

Data Index: 475172 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.8049. Min Act: -0.1700

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.7736. Min Act: -0.1700

Data Index: 779217 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.7110. Min Act: -0.1700

Data Index: 591450 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.7110. Min Act: -0.1700

Data Index: 940121 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.7110. Min Act: -0.1700

Data Index: 728421 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.7110. Min Act: -0.1700

Data Index: 602848 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6797. Min Act: -0.1700

Data Index: 743159 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.7110. Min Act: -0.1700

Data Index: 878778 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.7110. Min Act: -0.1700

Data Index: 434548 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6797. Min Act: -0.1700

Data Index: 634534 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6171. Min Act: -0.1700

Data Index: 639357 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6797. Min Act: -0.1700

Data Index: 1046213 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6484. Min Act: -0.1700

Data Index: 560183 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6797. Min Act: -0.1700

Data Index: 213032 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6484. Min Act: -0.1700

Data Index: 553687 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6797. Min Act: -0.1700

Data Index: 1237229 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 3.9612. Min Range: -3.9612

Max Act: 3.6171. Min Act: -0.1700

Data Index: 932588 (C4 (Web Text))

Max Activating Token Index: 964