Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 844 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1572. Min Range: -7.1572
Max Act: 7.1572. Min Act: -0.1700
Data Index: 1834851 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1572. Min Range: -7.1572
Max Act: 7.1260. Min Act: -0.1700
Data Index: 7947589 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.9697. Min Act: -0.1700
Data Index: 8505488 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.9697. Min Act: -0.1700
Data Index: 231837 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.9385. Min Act: -0.1700
Data Index: 1173567 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.9072. Min Act: -0.1700
Data Index: 5240393 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.9072. Min Act: -0.1700
Data Index: 5413310 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.9072. Min Act: -0.1700
Data Index: 1054009 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.9072. Min Act: -0.1700
Data Index: 3225997 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8760. Min Act: -0.1700
Data Index: 4379041 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8760. Min Act: -0.1700
Data Index: 7703008 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8447. Min Act: -0.1700
Data Index: 6622968 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8760. Min Act: -0.1700
Data Index: 5546761 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8447. Min Act: -0.1700
Data Index: 3528430 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8447. Min Act: -0.1700
Data Index: 7581735 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8135. Min Act: -0.1700
Data Index: 3613069 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.8135. Min Act: -0.1700
Data Index: 4822185 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.7822. Min Act: -0.1700
Data Index: 2423659 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.7822. Min Act: -0.1700
Data Index: 6659502 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1572. Min Range: -7.1572
Max Act: 6.7510. Min Act: -0.1700
Data Index: 6840798 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19