Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4735 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.7400. Min Act: -0.1700
Data Index: 8483867 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.7400. Min Act: -0.1700
Data Index: 8483864 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.5525. Min Act: -0.1700
Data Index: 2477428 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.6150. Min Act: -0.1700
Data Index: 8483870 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.6150. Min Act: -0.1700
Data Index: 1623644 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.6150. Min Act: -0.1700
Data Index: 232422 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.6150. Min Act: -0.1700
Data Index: 7562193 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.6150. Min Act: -0.1700
Data Index: 973809 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.5525. Min Act: -0.1700
Data Index: 4842173 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.4275. Min Act: -0.1700
Data Index: 4943311 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.4275. Min Act: -0.1700
Data Index: 138921 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.4275. Min Act: -0.1700
Data Index: 8483868 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.4275. Min Act: -0.1700
Data Index: 8483871 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.3650. Min Act: -0.1700
Data Index: 8483869 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.3650. Min Act: -0.1700
Data Index: 7415069 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.3650. Min Act: -0.1700
Data Index: 5515860 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.3025. Min Act: -0.1700
Data Index: 400672 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.3025. Min Act: -0.1700
Data Index: 3984292 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.3025. Min Act: -0.1700
Data Index: 2131087 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7400. Min Range: -9.7400
Max Act: 9.3025. Min Act: -0.1700
Data Index: 8483865 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19