Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.7340. Min Act: -0.1700
Data Index: 1586062 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.6715. Min Act: -0.1700
Data Index: 8396473 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5777. Min Act: -0.1700
Data Index: 8040363 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5777. Min Act: -0.1700
Data Index: 7500769 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5465. Min Act: -0.1700
Data Index: 1328479 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5465. Min Act: -0.1700
Data Index: 8425160 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5465. Min Act: -0.1700
Data Index: 7705067 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5465. Min Act: -0.1700
Data Index: 3210778 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5465. Min Act: -0.1699
Data Index: 6604721 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5465. Min Act: -0.1700
Data Index: 7104715 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 4106184 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 4960832 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 2558732 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 6581084 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 2410782 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 4086829 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 6520550 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.5152. Min Act: -0.1700
Data Index: 5494005 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.4840. Min Act: -0.1700
Data Index: 6886359 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7340. Min Range: -5.7340
Max Act: 5.4840. Min Act: -0.1700
Data Index: 8214884 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19