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

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

Neuron 1459 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: 5.1938. Min Range: -5.1938

Max Act: 5.1938. Min Act: -0.1700

Data Index: 234397 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.1313. Min Act: -0.1700

Data Index: 1262818 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.1000. Min Act: -0.1700

Data Index: 1302702 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.0375. Min Act: -0.1700

Data Index: 968480 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.1000. Min Act: -0.1700

Data Index: 1199961 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.0688. Min Act: -0.1700

Data Index: 607291 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.1000. Min Act: -0.1700

Data Index: 884188 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.1000. Min Act: -0.1700

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 5.1938. Min Range: -5.1938

Max Act: 5.0688. Min Act: -0.1700

Data Index: 1336984 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9750. Min Act: -0.1700

Data Index: 305906 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9750. Min Act: -0.1700

Data Index: 987852 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9438. Min Act: -0.1700

Data Index: 818437 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9750. Min Act: -0.1700

Data Index: 1233031 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9438. Min Act: -0.1700

Data Index: 526487 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9438. Min Act: -0.1700

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.8813. Min Act: -0.1700

Data Index: 742233 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9125. Min Act: -0.1700

Data Index: 939264 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.8813. Min Act: -0.1700

Data Index: 415484 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.9125. Min Act: -0.1700

Data Index: 137182 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 5.1938. Min Range: -5.1938

Max Act: 4.8813. Min Act: -0.1700

Data Index: 1315401 (C4 (Web Text))

Max Activating Token Index: 708