Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 2870648 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6725056 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 906773 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6542806 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6521836 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1697
Data Index: 6304039 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 1403446 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 7620253 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 5671249 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 778111 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 1936998 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 2318215 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 5263349 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1699
Data Index: 4662811 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 4502505 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1697
Data Index: 3786545 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6783552 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1699
Data Index: 1995272 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 1731836 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7890. Min Range: -5.7890
Max Act: 5.7890. Min Act: -0.1700
Data Index: 3369410 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19