Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4136 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.7478. Min Act: -0.1700
Data Index: 6823639 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.6228. Min Act: -0.1700
Data Index: 8618089 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5915. Min Act: -0.1700
Data Index: 2470687 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5915. Min Act: -0.1700
Data Index: 5164203 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5915. Min Act: -0.1700
Data Index: 5421678 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5603. Min Act: -0.1700
Data Index: 3744844 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5290. Min Act: -0.1700
Data Index: 8149136 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5603. Min Act: -0.1700
Data Index: 6558212 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5290. Min Act: -0.1700
Data Index: 3236625 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5603. Min Act: -0.1700
Data Index: 1019551 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.5290. Min Act: -0.1700
Data Index: 7201798 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4978. Min Act: -0.1697
Data Index: 361130 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4978. Min Act: -0.1700
Data Index: 5421676 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4978. Min Act: -0.1700
Data Index: 4134144 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4665. Min Act: -0.1700
Data Index: 6506116 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4665. Min Act: -0.1700
Data Index: 7990951 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4665. Min Act: -0.1700
Data Index: 5615974 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4665. Min Act: -0.1700
Data Index: 7813704 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4353. Min Act: -0.1700
Data Index: 7305369 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7478. Min Range: -6.7478
Max Act: 6.4040. Min Act: -0.1700
Data Index: 7976908 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19