Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 414 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0699. Min Range: -2.0699
Max Act: 2.0699. Min Act: -0.1700
Data Index: 3059926 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0699. Min Range: -2.0699
Max Act: 2.0194. Min Act: -0.1700
Data Index: 3357108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0699. Min Range: -2.0699
Max Act: 2.0025. Min Act: -0.1700
Data Index: 2667999 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.9856. Min Act: -0.1700
Data Index: 4670957 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.9856. Min Act: -0.1700
Data Index: 5889107 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.9347. Min Act: -0.1696
Data Index: 176435 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.9347. Min Act: -0.1700
Data Index: 178038 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.9177. Min Act: -0.1700
Data Index: 4940789 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8836. Min Act: -0.1700
Data Index: 2981995 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8836. Min Act: -0.1700
Data Index: 603149 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8836. Min Act: -0.1700
Data Index: 4066253 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8836. Min Act: -0.1699
Data Index: 5785051 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8836. Min Act: -0.1698
Data Index: 8729963 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8665. Min Act: -0.1700
Data Index: 176443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8494. Min Act: -0.1700
Data Index: 3320878 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8494. Min Act: -0.1700
Data Index: 5275385 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8665. Min Act: -0.1700
Data Index: 5240369 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8494. Min Act: -0.1700
Data Index: 5683787 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8494. Min Act: -0.1700
Data Index: 2946608 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0699. Min Range: -2.0699
Max Act: 1.8494. Min Act: -0.1700
Data Index: 3352615 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19