Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5299 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.6638. Min Act: -0.1699
Data Index: 547278 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.4138. Min Act: -0.1700
Data Index: 5500888 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.3513. Min Act: -0.1700
Data Index: 8446564 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.2888. Min Act: -0.1700
Data Index: 1242025 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.2888. Min Act: -0.1700
Data Index: 1242022 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.2263. Min Act: -0.1700
Data Index: 1242004 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.2263. Min Act: -0.1700
Data Index: 4589436 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.2888. Min Act: -0.1700
Data Index: 5500887 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.2263. Min Act: -0.1700
Data Index: 5500886 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1638. Min Act: -0.1699
Data Index: 8420397 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.2263. Min Act: -0.1700
Data Index: 1242032 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1638. Min Act: -0.1700
Data Index: 1242001 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1013. Min Act: -0.1699
Data Index: 5500868 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1013. Min Act: -0.1700
Data Index: 1169359 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1638. Min Act: -0.1700
Data Index: 1242005 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1638. Min Act: -0.1700
Data Index: 4589429 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1638. Min Act: -0.1699
Data Index: 7869300 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1638. Min Act: -0.1700
Data Index: 934871 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1013. Min Act: -0.1700
Data Index: 2996884 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6638. Min Range: -8.6638
Max Act: 8.1013. Min Act: -0.1698
Data Index: 4484771 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19