Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.3579. Min Act: -0.1700
Data Index: 5827342 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.2642. Min Act: -0.1700
Data Index: 4291197 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.2329. Min Act: -0.1700
Data Index: 8480293 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.2642. Min Act: -0.1700
Data Index: 8340470 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.2329. Min Act: -0.1700
Data Index: 748020 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.2017. Min Act: -0.1700
Data Index: 3862210 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.1704. Min Act: -0.1700
Data Index: 2504486 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.1704. Min Act: -0.1700
Data Index: 5152238 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.2017. Min Act: -0.1700
Data Index: 7242272 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.1392. Min Act: -0.1700
Data Index: 3031150 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.1079. Min Act: -0.1700
Data Index: 4154758 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.1079. Min Act: -0.1700
Data Index: 3337461 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.1079. Min Act: -0.1700
Data Index: 6739743 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.0767. Min Act: -0.1700
Data Index: 2922128 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.0767. Min Act: -0.1700
Data Index: 2502523 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.0454. Min Act: -0.1700
Data Index: 5709716 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.0454. Min Act: -0.1700
Data Index: 2057963 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.0454. Min Act: -0.1700
Data Index: 2293664 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.0454. Min Act: -0.1700
Data Index: 1331083 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3579. Min Range: -5.3579
Max Act: 5.0454. Min Act: -0.1700
Data Index: 6756315 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19