Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4224 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.9823. Min Act: -0.1700
Data Index: 1713985 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.9510. Min Act: -0.1700
Data Index: 8073432 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.9198. Min Act: -0.1700
Data Index: 3830213 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.9198. Min Act: -0.1700
Data Index: 815597 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.9198. Min Act: -0.1700
Data Index: 3423513 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8885. Min Act: -0.1700
Data Index: 5805577 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8885. Min Act: -0.1700
Data Index: 2282188 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8572. Min Act: -0.1700
Data Index: 6427687 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8572. Min Act: -0.1700
Data Index: 2145392 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8572. Min Act: -0.1700
Data Index: 4195940 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8572. Min Act: -0.1700
Data Index: 2055967 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8572. Min Act: -0.1700
Data Index: 2558534 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8260. Min Act: -0.1700
Data Index: 4144182 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8260. Min Act: -0.1700
Data Index: 2661551 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.8260. Min Act: -0.1700
Data Index: 5523870 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.7947. Min Act: -0.1700
Data Index: 1954350 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.7947. Min Act: -0.1700
Data Index: 4687202 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.7947. Min Act: -0.1700
Data Index: 979307 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.7634. Min Act: -0.1700
Data Index: 4940815 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9823. Min Range: -3.9823
Max Act: 3.7634. Min Act: -0.1700
Data Index: 2396592 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19