Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4572 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.3028. Min Act: -0.1700
Data Index: 3821712 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.2403. Min Act: -0.1700
Data Index: 4411371 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.2403. Min Act: -0.1700
Data Index: 6892969 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 5590620 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 5465878 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 5254774 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1778. Min Act: -0.1700
Data Index: 1933132 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1778. Min Act: -0.1700
Data Index: 4226379 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1778. Min Act: -0.1700
Data Index: 1003413 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1778. Min Act: -0.1699
Data Index: 5866742 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1778. Min Act: -0.1700
Data Index: 8674809 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 6618784 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 1282113 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 7165176 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 4308676 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 2278027 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 2355837 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 7539683 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 5254770 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3028. Min Range: -5.3028
Max Act: 5.1466. Min Act: -0.1700
Data Index: 3614980 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19