Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5624. Min Range: -7.5624
Max Act: 7.5624. Min Act: -0.1700
Data Index: 2787372 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5624. Min Range: -7.5624
Max Act: 7.2499. Min Act: -0.1700
Data Index: 560132 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5624. Min Range: -7.5624
Max Act: 7.2499. Min Act: -0.1700
Data Index: 5509849 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.9999. Min Act: -0.1700
Data Index: 630667 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5624. Min Range: -7.5624
Max Act: 7.0624. Min Act: -0.1700
Data Index: 1740187 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.9999. Min Act: -0.1700
Data Index: 6451569 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.9999. Min Act: -0.1700
Data Index: 4566241 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.8437. Min Act: -0.1700
Data Index: 3708852 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.9374. Min Act: -0.1700
Data Index: 6930210 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.8437. Min Act: -0.1700
Data Index: 7878390 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.8124. Min Act: -0.1700
Data Index: 8105286 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.8124. Min Act: -0.1700
Data Index: 3708851 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.8124. Min Act: -0.1700
Data Index: 2241258 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.7812. Min Act: -0.1700
Data Index: 6176426 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.7499. Min Act: -0.1700
Data Index: 6090192 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.7187. Min Act: -0.1700
Data Index: 1953644 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.7187. Min Act: -0.1700
Data Index: 8060594 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.7187. Min Act: -0.1700
Data Index: 1073590 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.7187. Min Act: -0.1700
Data Index: 1406156 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5624. Min Range: -7.5624
Max Act: 6.7187. Min Act: -0.1700
Data Index: 5781232 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19