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

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

Neuron 933 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1532. Min Range: -5.1532

Max Act: 5.1532. Min Act: -0.1700

Data Index: 143747 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 5.1532. Min Range: -5.1532

Max Act: 5.0595. Min Act: -0.1700

Data Index: 201807 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 5.1532. Min Range: -5.1532

Max Act: 5.0595. Min Act: -0.1700

Data Index: 23145 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 5.1532. Min Range: -5.1532

Max Act: 5.0907. Min Act: -0.1700

Data Index: 283 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 5.1532. Min Range: -5.1532

Max Act: 5.0282. Min Act: -0.1700

Data Index: 294426 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9970. Min Act: -0.1700

Data Index: 737549 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9970. Min Act: -0.1700

Data Index: 455851 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9657. Min Act: -0.1700

Data Index: 860039 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9657. Min Act: -0.1700

Data Index: 434487 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9345. Min Act: -0.1700

Data Index: 370813 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9345. Min Act: -0.1699

Data Index: 1125876 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9970. Min Act: -0.1700

Data Index: 159503 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9345. Min Act: -0.1689

Data Index: 193396 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.9032. Min Act: -0.1699

Data Index: 126036 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.8407. Min Act: -0.1700

Data Index: 309785 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.8720. Min Act: -0.1700

Data Index: 724554 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.8720. Min Act: -0.1700

Data Index: 348104 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.8720. Min Act: -0.1700

Data Index: 379902 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.8095. Min Act: -0.1700

Data Index: 709501 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 5.1532. Min Range: -5.1532

Max Act: 4.8407. Min Act: -0.1700

Data Index: 11821 (C4 (Web Text))

Max Activating Token Index: 301