Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1256. Min Range: -6.1256
Max Act: 6.1256. Min Act: -0.1700
Data Index: 7928792 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1256. Min Range: -6.1256
Max Act: 6.0318. Min Act: -0.1700
Data Index: 6540825 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.9068. Min Act: -0.1700
Data Index: 4951367 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8443. Min Act: -0.1700
Data Index: 5995650 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8756. Min Act: -0.1700
Data Index: 764028 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8756. Min Act: -0.1700
Data Index: 1215364 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4503005 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8443. Min Act: -0.1700
Data Index: 2421985 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8443. Min Act: -0.1700
Data Index: 7443165 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8443. Min Act: -0.1700
Data Index: 8256626 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4711103 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8131. Min Act: -0.1700
Data Index: 6644161 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8131. Min Act: -0.1700
Data Index: 3502165 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.7818. Min Act: -0.1700
Data Index: 8742052 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8131. Min Act: -0.1700
Data Index: 2435060 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8131. Min Act: -0.1700
Data Index: 6120810 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8131. Min Act: -0.1700
Data Index: 570809 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.7818. Min Act: -0.1700
Data Index: 7470289 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.8131. Min Act: -0.1700
Data Index: 2277773 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1256. Min Range: -6.1256
Max Act: 5.7818. Min Act: -0.1700
Data Index: 8113045 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19