Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2421 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0943. Min Act: -0.1700
Data Index: 506394 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0943. Min Act: -0.1700
Data Index: 1956485 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0943. Min Act: -0.1700
Data Index: 3325612 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0631. Min Act: -0.1700
Data Index: 1956486 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0318. Min Act: -0.1700
Data Index: 796166 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0318. Min Act: -0.1700
Data Index: 566391 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0318. Min Act: -0.1700
Data Index: 506391 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0943. Min Range: -5.0943
Max Act: 5.0006. Min Act: -0.1700
Data Index: 8829214 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9693. Min Act: -0.1700
Data Index: 4596415 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9381. Min Act: -0.1700
Data Index: 4272762 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9693. Min Act: -0.1700
Data Index: 5906547 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9381. Min Act: -0.1700
Data Index: 7413407 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9068. Min Act: -0.1700
Data Index: 506395 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9068. Min Act: -0.1700
Data Index: 1592400 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9068. Min Act: -0.1700
Data Index: 1956484 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9068. Min Act: -0.1700
Data Index: 8784805 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.9068. Min Act: -0.1700
Data Index: 619866 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.8756. Min Act: -0.1700
Data Index: 1129001 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.8756. Min Act: -0.1700
Data Index: 1672640 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0943. Min Range: -5.0943
Max Act: 4.8756. Min Act: -0.1700
Data Index: 6076443 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19