Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4500 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.6955. Min Act: -0.1700
Data Index: 2425391 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.6955. Min Act: -0.1700
Data Index: 99586 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.6955. Min Act: -0.1700
Data Index: 8203196 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.6642. Min Act: -0.1700
Data Index: 7405635 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.6486. Min Act: -0.1700
Data Index: 2359557 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.6016. Min Act: -0.1700
Data Index: 1004785 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.6173. Min Act: -0.1700
Data Index: 1072268 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5860. Min Act: -0.1700
Data Index: 7555832 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5860. Min Act: -0.1700
Data Index: 269973 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5547. Min Act: -0.1700
Data Index: 6005941 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5390. Min Act: -0.1700
Data Index: 909244 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5547. Min Act: -0.1700
Data Index: 5224828 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5390. Min Act: -0.1700
Data Index: 341602 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5547. Min Act: -0.1700
Data Index: 4016691 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5390. Min Act: -0.1700
Data Index: 2386813 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5234. Min Act: -0.1700
Data Index: 6736942 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.5077. Min Act: -0.1700
Data Index: 1038355 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.4920. Min Act: -0.1700
Data Index: 704011 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.4764. Min Act: -0.1700
Data Index: 1727154 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6955. Min Range: -3.6955
Max Act: 3.4607. Min Act: -0.1700
Data Index: 568340 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19