Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4738 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.4782. Min Act: -0.1700
Data Index: 6918481 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.3532. Min Act: -0.1700
Data Index: 2963538 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.2907. Min Act: -0.1700
Data Index: 4045691 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.2595. Min Act: -0.1700
Data Index: 3669697 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1970. Min Act: -0.1700
Data Index: 24000 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1970. Min Act: -0.1700
Data Index: 47969 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1657. Min Act: -0.1700
Data Index: 4779629 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1970. Min Act: -0.1700
Data Index: 4694612 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1345. Min Act: -0.1700
Data Index: 7988133 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1345. Min Act: -0.1700
Data Index: 4760236 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1345. Min Act: -0.1700
Data Index: 6923257 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1032. Min Act: -0.1700
Data Index: 2837377 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1032. Min Act: -0.1700
Data Index: 1354792 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1032. Min Act: -0.1700
Data Index: 7893057 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.0720. Min Act: -0.1700
Data Index: 2262640 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.0720. Min Act: -0.1700
Data Index: 1169427 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.0720. Min Act: -0.1700
Data Index: 2568851 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.0720. Min Act: -0.1700
Data Index: 6396561 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.1032. Min Act: -0.1700
Data Index: 346938 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4782. Min Range: -6.4782
Max Act: 6.0720. Min Act: -0.1700
Data Index: 7124136 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19