Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 538 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.3951. Min Act: -0.1700
Data Index: 7071733 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.3951. Min Act: -0.1700
Data Index: 4041695 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.3014. Min Act: -0.1700
Data Index: 283934 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.3014. Min Act: -0.1700
Data Index: 6748335 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 5382904 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 6233966 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 916252 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 1051867 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 1527505 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 6379068 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 2501136 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2389. Min Act: -0.1700
Data Index: 7895554 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2389. Min Act: -0.1700
Data Index: 6386049 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2389. Min Act: -0.1700
Data Index: 1459308 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 4263657 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 7664376 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 5203016 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 7633208 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 6786907 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3951. Min Range: -6.3951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 6943620 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19