Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 582 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0345. Min Range: -4.0345

Max Act: 4.0345. Min Act: -0.1700

Data Index: 1032867 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 4.0345. Min Range: -4.0345

Max Act: 4.0032. Min Act: -0.1692

Data Index: 443494 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.9720. Min Act: -0.1700

Data Index: 123432 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.9720. Min Act: -0.1700

Data Index: 43778 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.9720. Min Act: -0.1700

Data Index: 274959 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.9094. Min Act: -0.1700

Data Index: 846454 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8782. Min Act: -0.1700

Data Index: 604661 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8625. Min Act: -0.1700

Data Index: 844307 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8782. Min Act: -0.1700

Data Index: 547148 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8625. Min Act: -0.1700

Data Index: 1106071 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8312. Min Act: -0.1682

Data Index: 908137 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8000. Min Act: -0.1700

Data Index: 98493 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8156. Min Act: -0.1700

Data Index: 311337 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8469. Min Act: -0.1700

Data Index: 285729 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8000. Min Act: -0.1700

Data Index: 1032202 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8156. Min Act: -0.1700

Data Index: 323249 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.7843. Min Act: -0.1700

Data Index: 701388 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.7687. Min Act: -0.1695

Data Index: 635344 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.8000. Min Act: -0.1700

Data Index: 484980 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 4.0345. Min Range: -4.0345

Max Act: 3.7687. Min Act: -0.1700

Data Index: 138541 (C4 (Web Text))

Max Activating Token Index: 729