Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.1027. Min Act: -0.1700
Data Index: 7553756 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.1027. Min Act: -0.1700
Data Index: 6846325 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.1027. Min Act: -0.1700
Data Index: 7289826 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 6137520 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 3716056 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 5937669 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 5749055 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 1640855 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 1563048 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 1413110 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 6915691 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0860. Min Act: -0.1700
Data Index: 2646697 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0692. Min Act: -0.1700
Data Index: 3545183 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0692. Min Act: -0.1700
Data Index: 3632656 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0692. Min Act: -0.1700
Data Index: 2706851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0692. Min Act: -0.1700
Data Index: 8036147 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0524. Min Act: -0.1700
Data Index: 3790614 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0524. Min Act: -0.1700
Data Index: 5192311 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0356. Min Act: -0.1700
Data Index: 5479119 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1027. Min Range: -2.1027
Max Act: 2.0692. Min Act: -0.1700
Data Index: 4325957 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19