Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4313 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.3767. Min Act: -0.1700
Data Index: 3157509 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.3767. Min Act: -0.1700
Data Index: 8784526 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.3142. Min Act: -0.1700
Data Index: 5297499 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0955. Min Act: -0.1700
Data Index: 3752009 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0955. Min Act: -0.1700
Data Index: 2946966 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0955. Min Act: -0.1700
Data Index: 1384217 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0330. Min Act: -0.1700
Data Index: 1564028 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0642. Min Act: -0.1700
Data Index: 2657260 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0642. Min Act: -0.1700
Data Index: 2636922 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0330. Min Act: -0.1700
Data Index: 6542908 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0330. Min Act: -0.1700
Data Index: 6003755 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0330. Min Act: -0.1700
Data Index: 3764055 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0330. Min Act: -0.1700
Data Index: 2185351 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0017. Min Act: -0.1700
Data Index: 4884725 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0017. Min Act: -0.1700
Data Index: 3270708 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0017. Min Act: -0.1700
Data Index: 5767449 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0017. Min Act: -0.1700
Data Index: 961342 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3767. Min Range: -5.3767
Max Act: 5.0017. Min Act: -0.1700
Data Index: 6542907 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3767. Min Range: -5.3767
Max Act: 4.9705. Min Act: -0.1700
Data Index: 8826541 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3767. Min Range: -5.3767
Max Act: 4.9392. Min Act: -0.1700
Data Index: 5217631 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19