Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7850. Min Range: -7.7850
Max Act: 7.7850. Min Act: -0.1700
Data Index: 2188251 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7850. Min Range: -7.7850
Max Act: 7.0975. Min Act: -0.1700
Data Index: 5894945 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.9725. Min Act: -0.1700
Data Index: 745266 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.9725. Min Act: -0.1700
Data Index: 7538221 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.9413. Min Act: -0.1700
Data Index: 106749 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.9100. Min Act: -0.1700
Data Index: 5473658 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.9100. Min Act: -0.1700
Data Index: 5552678 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.8475. Min Act: -0.1700
Data Index: 3372420 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.8788. Min Act: -0.1700
Data Index: 3382561 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.8788. Min Act: -0.1700
Data Index: 5897276 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.8163. Min Act: -0.1700
Data Index: 5375290 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.8163. Min Act: -0.1700
Data Index: 8524814 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.7850. Min Act: -0.1700
Data Index: 8624802 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.7538. Min Act: -0.1700
Data Index: 5894944 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.7538. Min Act: -0.1700
Data Index: 1600078 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.7850. Min Act: -0.1700
Data Index: 8134803 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.7225. Min Act: -0.1700
Data Index: 8394182 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.7225. Min Act: -0.1700
Data Index: 3551349 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.6913. Min Act: -0.1700
Data Index: 1551343 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7850. Min Range: -7.7850
Max Act: 6.6600. Min Act: -0.1700
Data Index: 6800627 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19