Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0841. Min Range: -7.0841
Max Act: 7.0841. Min Act: -0.1700
Data Index: 3386692 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.8654. Min Act: -0.1700
Data Index: 7958732 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.7404. Min Act: -0.1700
Data Index: 5035998 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.7404. Min Act: -0.1700
Data Index: 8213876 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.7091. Min Act: -0.1700
Data Index: 3048227 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.6466. Min Act: -0.1700
Data Index: 6252719 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.6466. Min Act: -0.1700
Data Index: 7578060 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.6154. Min Act: -0.1700
Data Index: 8815908 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.6154. Min Act: -0.1700
Data Index: 1574110 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.5529. Min Act: -0.1700
Data Index: 8762911 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.5216. Min Act: -0.1700
Data Index: 3220827 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.4591. Min Act: -0.1700
Data Index: 7764831 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3966. Min Act: -0.1700
Data Index: 3881348 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3341. Min Act: -0.1700
Data Index: 4754065 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3654. Min Act: -0.1700
Data Index: 5793639 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3341. Min Act: -0.1700
Data Index: 2956702 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3341. Min Act: -0.1700
Data Index: 1639391 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3029. Min Act: -0.1700
Data Index: 8452436 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3029. Min Act: -0.1700
Data Index: 4321139 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0841. Min Range: -7.0841
Max Act: 6.3029. Min Act: -0.1700
Data Index: 1444196 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19