Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7998. Min Act: -0.1700
Data Index: 2251556 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7915. Min Act: -0.1700
Data Index: 7260682 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7748. Min Act: -0.1699
Data Index: 2461527 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7498. Min Act: -0.1700
Data Index: 7172521 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7498. Min Act: -0.1700
Data Index: 8160123 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7498. Min Act: -0.1700
Data Index: 6371671 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7581. Min Act: -0.1700
Data Index: 6001456 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7416. Min Act: -0.1690
Data Index: 7707977 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7251. Min Act: -0.1700
Data Index: 2876015 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7169. Min Act: -0.1700
Data Index: 2351683 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7169. Min Act: -0.1700
Data Index: 3500305 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7087. Min Act: -0.1688
Data Index: 7746151 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.6924. Min Act: -0.1700
Data Index: 3413757 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7005. Min Act: -0.1699
Data Index: 3269746 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7005. Min Act: -0.1699
Data Index: 5705515 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7005. Min Act: -0.1700
Data Index: 8265532 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7005. Min Act: -0.1698
Data Index: 8560497 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.7005. Min Act: -0.1700
Data Index: 4065097 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.6924. Min Act: -0.1693
Data Index: 2314881 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7998. Min Range: -0.7998
Max Act: 0.6924. Min Act: -0.1700
Data Index: 3505403 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19