Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.6135. Min Act: -0.1700
Data Index: 5137670 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.5510. Min Act: -0.1700
Data Index: 531123 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.5198. Min Act: -0.1700
Data Index: 5137666 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.5198. Min Act: -0.1700
Data Index: 8376132 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.4260. Min Act: -0.1700
Data Index: 372873 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.3323. Min Act: -0.1700
Data Index: 3197842 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.2698. Min Act: -0.1700
Data Index: 3197843 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.2698. Min Act: -0.1700
Data Index: 7728707 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.2073. Min Act: -0.1700
Data Index: 8376130 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.1760. Min Act: -0.1700
Data Index: 8376140 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.1760. Min Act: -0.1700
Data Index: 1874302 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.1760. Min Act: -0.1700
Data Index: 5137667 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.1760. Min Act: -0.1700
Data Index: 6279797 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.2073. Min Act: -0.1700
Data Index: 5137678 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.1448. Min Act: -0.1700
Data Index: 5565939 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0823. Min Act: -0.1700
Data Index: 5137679 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0510. Min Act: -0.1700
Data Index: 737415 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0823. Min Act: -0.1700
Data Index: 5137668 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0823. Min Act: -0.1700
Data Index: 1097052 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6135. Min Range: -8.6135
Max Act: 8.0510. Min Act: -0.1700
Data Index: 531118 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19