Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1614 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0853. Min Range: -6.0853
Max Act: 6.0853. Min Act: -0.1700
Data Index: 6103038 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0853. Min Range: -6.0853
Max Act: 6.0541. Min Act: -0.1700
Data Index: 6685426 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0853. Min Range: -6.0853
Max Act: 6.0541. Min Act: -0.1700
Data Index: 7782573 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0853. Min Range: -6.0853
Max Act: 6.0228. Min Act: -0.1700
Data Index: 6235636 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.9916. Min Act: -0.1700
Data Index: 8204255 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0853. Min Range: -6.0853
Max Act: 6.0228. Min Act: -0.1700
Data Index: 575827 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.9291. Min Act: -0.1700
Data Index: 3384190 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.8666. Min Act: -0.1700
Data Index: 1406644 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.8666. Min Act: -0.1700
Data Index: 652448 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.7728. Min Act: -0.1700
Data Index: 4362309 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.7416. Min Act: -0.1700
Data Index: 5331055 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.7103. Min Act: -0.1700
Data Index: 5349516 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.7103. Min Act: -0.1700
Data Index: 6584275 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.7103. Min Act: -0.1700
Data Index: 1658225 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.6791. Min Act: -0.1700
Data Index: 8434506 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.6478. Min Act: -0.1700
Data Index: 2832824 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.6478. Min Act: -0.1700
Data Index: 5012489 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.6166. Min Act: -0.1700
Data Index: 5046621 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.6166. Min Act: -0.1700
Data Index: 7597442 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0853. Min Range: -6.0853
Max Act: 5.5853. Min Act: -0.1700
Data Index: 3008419 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19