Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1748 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1767. Min Range: -8.1767
Max Act: 8.1767. Min Act: -0.1700
Data Index: 2012054 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1767. Min Range: -8.1767
Max Act: 8.1142. Min Act: -0.1700
Data Index: 6866404 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.9579. Min Act: -0.1700
Data Index: 7544810 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.8642. Min Act: -0.1700
Data Index: 7695140 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.8642. Min Act: -0.1700
Data Index: 7075520 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.8642. Min Act: -0.1700
Data Index: 2709112 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.8329. Min Act: -0.1700
Data Index: 1208438 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.8017. Min Act: -0.1700
Data Index: 3909772 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.8329. Min Act: -0.1700
Data Index: 6866387 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.8329. Min Act: -0.1700
Data Index: 8214656 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.7704. Min Act: -0.1700
Data Index: 1143651 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.7704. Min Act: -0.1700
Data Index: 8785548 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.7392. Min Act: -0.1700
Data Index: 2256690 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.6767. Min Act: -0.1700
Data Index: 6353552 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.6767. Min Act: -0.1700
Data Index: 7005445 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.6767. Min Act: -0.1700
Data Index: 1475018 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.6767. Min Act: -0.1700
Data Index: 4389652 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.6767. Min Act: -0.1700
Data Index: 6286020 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.6454. Min Act: -0.1700
Data Index: 3076477 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1767. Min Range: -8.1767
Max Act: 7.6454. Min Act: -0.1700
Data Index: 7672677 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19