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

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

Neuron 1296 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: 4.0038. Min Range: -4.0038

Max Act: 4.0038. Min Act: -0.1700

Data Index: 1251156 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 4.0038. Min Range: -4.0038

Max Act: 4.0038. Min Act: -0.1700

Data Index: 1198226 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9725. Min Act: -0.1700

Data Index: 941882 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9412. Min Act: -0.1700

Data Index: 427967 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9412. Min Act: -0.1700

Data Index: 92248 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 1198495 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9412. Min Act: -0.1700

Data Index: 957293 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 945582 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 881459 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 499260 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 251784 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.8787. Min Act: -0.1700

Data Index: 672544 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 600531 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 724023 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 792673 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 832800 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9412. Min Act: -0.1700

Data Index: 383431 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.9100. Min Act: -0.1700

Data Index: 633213 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.8474. Min Act: -0.1700

Data Index: 1080193 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 4.0038. Min Range: -4.0038

Max Act: 3.8787. Min Act: -0.1700

Data Index: 870017 (C4 (Web Text))

Max Activating Token Index: 820