Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6397 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.1724. Min Act: -0.1700
Data Index: 3680827 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.1724. Min Act: -0.1700
Data Index: 5294798 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.1724. Min Act: -0.1700
Data Index: 8644668 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.1099. Min Act: -0.1700
Data Index: 4305711 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.1099. Min Act: -0.1700
Data Index: 5589206 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0474. Min Act: -0.1700
Data Index: 5657995 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0787. Min Act: -0.1700
Data Index: 7657993 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0474. Min Act: -0.1700
Data Index: 3968741 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0474. Min Act: -0.1700
Data Index: 781034 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0162. Min Act: -0.1700
Data Index: 6273722 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0162. Min Act: -0.1700
Data Index: 2291053 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0162. Min Act: -0.1700
Data Index: 8194642 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1724. Min Range: -6.1724
Max Act: 6.0474. Min Act: -0.1700
Data Index: 8730483 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1724. Min Range: -6.1724
Max Act: 5.9849. Min Act: -0.1700
Data Index: 7615164 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1724. Min Range: -6.1724
Max Act: 5.9849. Min Act: -0.1700
Data Index: 2584438 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1724. Min Range: -6.1724
Max Act: 5.9537. Min Act: -0.1700
Data Index: 4685262 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1724. Min Range: -6.1724
Max Act: 5.9849. Min Act: -0.1700
Data Index: 3912759 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1724. Min Range: -6.1724
Max Act: 5.9849. Min Act: -0.1700
Data Index: 7953333 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1724. Min Range: -6.1724
Max Act: 5.9849. Min Act: -0.1700
Data Index: 3794156 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1724. Min Range: -6.1724
Max Act: 5.9849. Min Act: -0.1700
Data Index: 5106543 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19