Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.3016. Min Act: -0.1700
Data Index: 2372390 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.2078. Min Act: -0.1700
Data Index: 2434499 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.1453. Min Act: -0.1700
Data Index: 5527072 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0828. Min Act: -0.1700
Data Index: 1411738 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0828. Min Act: -0.1700
Data Index: 1941451 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0515. Min Act: -0.1700
Data Index: 2252634 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0828. Min Act: -0.1700
Data Index: 8112496 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0828. Min Act: -0.1700
Data Index: 8167048 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0515. Min Act: -0.1700
Data Index: 8593655 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0203. Min Act: -0.1700
Data Index: 7122869 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0203. Min Act: -0.1700
Data Index: 6714786 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9890. Min Act: -0.1700
Data Index: 5398048 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9890. Min Act: -0.1700
Data Index: 5237766 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9578. Min Act: -0.1700
Data Index: 8460903 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9890. Min Act: -0.1700
Data Index: 4669054 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9890. Min Act: -0.1700
Data Index: 7154100 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3016. Min Range: -4.3016
Max Act: 4.0203. Min Act: -0.1700
Data Index: 3423374 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9890. Min Act: -0.1700
Data Index: 6916902 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9578. Min Act: -0.1700
Data Index: 6610559 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3016. Min Range: -4.3016
Max Act: 3.9265. Min Act: -0.1700
Data Index: 5795148 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19