Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2115 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3777. Min Range: -6.3777
Max Act: 6.3777. Min Act: -0.1700
Data Index: 1534782 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3777. Min Range: -6.3777
Max Act: 6.2527. Min Act: -0.1700
Data Index: 7555782 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3777. Min Range: -6.3777
Max Act: 6.0652. Min Act: -0.1700
Data Index: 8334142 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3777. Min Range: -6.3777
Max Act: 6.0027. Min Act: -0.1700
Data Index: 2255805 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3777. Min Range: -6.3777
Max Act: 6.0027. Min Act: -0.1700
Data Index: 6213159 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3777. Min Range: -6.3777
Max Act: 6.0027. Min Act: -0.1700
Data Index: 8192170 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3777. Min Range: -6.3777
Max Act: 6.0027. Min Act: -0.1700
Data Index: 8334141 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.9715. Min Act: -0.1700
Data Index: 4731093 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.9715. Min Act: -0.1700
Data Index: 4931048 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.9715. Min Act: -0.1700
Data Index: 5223386 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.9402. Min Act: -0.1700
Data Index: 8403164 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.9402. Min Act: -0.1700
Data Index: 2044729 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.9090. Min Act: -0.1700
Data Index: 7318243 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.9090. Min Act: -0.1700
Data Index: 1342973 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.8777. Min Act: -0.1700
Data Index: 70540 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.8777. Min Act: -0.1700
Data Index: 4731092 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.8777. Min Act: -0.1700
Data Index: 5286919 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.8777. Min Act: -0.1700
Data Index: 8437050 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8295347 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3777. Min Range: -6.3777
Max Act: 5.7840. Min Act: -0.1700
Data Index: 724904 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19