Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3323 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1532. Min Range: -6.1532
Max Act: 6.1532. Min Act: -0.1700
Data Index: 5672706 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1532. Min Range: -6.1532
Max Act: 6.1532. Min Act: -0.1700
Data Index: 2849724 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1532. Min Range: -6.1532
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3674044 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1532. Min Range: -6.1532
Max Act: 6.1219. Min Act: -0.1700
Data Index: 5042269 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1532. Min Range: -6.1532
Max Act: 6.0594. Min Act: -0.1700
Data Index: 7396398 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.9969. Min Act: -0.1700
Data Index: 360573 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.9344. Min Act: -0.1700
Data Index: 187318 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.9344. Min Act: -0.1700
Data Index: 8708675 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.9032. Min Act: -0.1700
Data Index: 4460872 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.8719. Min Act: -0.1700
Data Index: 5015982 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.8719. Min Act: -0.1700
Data Index: 5368780 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.8094. Min Act: -0.1700
Data Index: 3550385 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.8094. Min Act: -0.1700
Data Index: 7655562 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.7782. Min Act: -0.1700
Data Index: 4217654 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.7782. Min Act: -0.1700
Data Index: 5158307 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.7469. Min Act: -0.1700
Data Index: 4169618 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.7157. Min Act: -0.1700
Data Index: 6127740 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.7157. Min Act: -0.1700
Data Index: 2072471 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.6844. Min Act: -0.1700
Data Index: 7157550 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1532. Min Range: -6.1532
Max Act: 5.6844. Min Act: -0.1700
Data Index: 3489009 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19