Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1544. Min Range: -6.1544
Max Act: 6.1544. Min Act: -0.1700
Data Index: 454525 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1544. Min Range: -6.1544
Max Act: 6.0294. Min Act: -0.1700
Data Index: 3582472 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1544. Min Range: -6.1544
Max Act: 6.0294. Min Act: -0.1700
Data Index: 1742049 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.9669. Min Act: -0.1700
Data Index: 4860035 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.9357. Min Act: -0.1700
Data Index: 3582471 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5407351 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5660023 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.8732. Min Act: -0.1700
Data Index: 4792864 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.8419. Min Act: -0.1700
Data Index: 2901565 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.8107. Min Act: -0.1700
Data Index: 7938380 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7794. Min Act: -0.1700
Data Index: 4009176 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7794. Min Act: -0.1700
Data Index: 2854162 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.8107. Min Act: -0.1700
Data Index: 952074 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7794. Min Act: -0.1700
Data Index: 8147053 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7482. Min Act: -0.1700
Data Index: 7571061 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7169. Min Act: -0.1700
Data Index: 3560686 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7482. Min Act: -0.1700
Data Index: 1615032 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7169. Min Act: -0.1700
Data Index: 5223971 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7169. Min Act: -0.1700
Data Index: 7190778 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1544. Min Range: -6.1544
Max Act: 5.7169. Min Act: -0.1700
Data Index: 2586989 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19