Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3637. Min Range: -6.3637
Max Act: 6.3637. Min Act: -0.1700
Data Index: 3784225 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3637. Min Range: -6.3637
Max Act: 6.2699. Min Act: -0.1700
Data Index: 503026 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3637. Min Range: -6.3637
Max Act: 6.0512. Min Act: -0.1700
Data Index: 5650204 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3637. Min Range: -6.3637
Max Act: 6.0512. Min Act: -0.1700
Data Index: 8160326 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3637. Min Range: -6.3637
Max Act: 6.0824. Min Act: -0.1700
Data Index: 3945137 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3637. Min Range: -6.3637
Max Act: 6.0199. Min Act: -0.1700
Data Index: 2136427 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3637. Min Range: -6.3637
Max Act: 6.0199. Min Act: -0.1700
Data Index: 3381912 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.9887. Min Act: -0.1700
Data Index: 6176732 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.9887. Min Act: -0.1700
Data Index: 6998194 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.9574. Min Act: -0.1700
Data Index: 1930842 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.9574. Min Act: -0.1700
Data Index: 3770159 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.9262. Min Act: -0.1700
Data Index: 6713839 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.9262. Min Act: -0.1700
Data Index: 4114464 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.8949. Min Act: -0.1700
Data Index: 2463261 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.8949. Min Act: -0.1700
Data Index: 4827698 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.8637. Min Act: -0.1700
Data Index: 3736397 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.8637. Min Act: -0.1700
Data Index: 10925 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.8637. Min Act: -0.1700
Data Index: 6549594 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.8637. Min Act: -0.1700
Data Index: 413436 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3637. Min Range: -6.3637
Max Act: 5.8637. Min Act: -0.1700
Data Index: 2407687 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19