Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5794 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6954. Min Range: -8.6954
Max Act: 8.6954. Min Act: -0.1700
Data Index: 3099560 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6954. Min Range: -8.6954
Max Act: 8.0704. Min Act: -0.1700
Data Index: 5463009 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.9454. Min Act: -0.1700
Data Index: 5327054 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.9141. Min Act: -0.1700
Data Index: 4044855 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.8829. Min Act: -0.1700
Data Index: 484995 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.8516. Min Act: -0.1700
Data Index: 3961649 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.8516. Min Act: -0.1700
Data Index: 3073786 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.8516. Min Act: -0.1700
Data Index: 4885209 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.8204. Min Act: -0.1700
Data Index: 305324 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.8516. Min Act: -0.1700
Data Index: 5204963 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.7579. Min Act: -0.1700
Data Index: 5225253 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.7579. Min Act: -0.1700
Data Index: 5010135 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.7579. Min Act: -0.1700
Data Index: 759683 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.7579. Min Act: -0.1700
Data Index: 305325 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.7266. Min Act: -0.1700
Data Index: 2874129 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.7579. Min Act: -0.1700
Data Index: 1001739 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.6954. Min Act: -0.1700
Data Index: 586754 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.6641. Min Act: -0.1700
Data Index: 6046015 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.6641. Min Act: -0.1700
Data Index: 8082193 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6954. Min Range: -8.6954
Max Act: 7.6329. Min Act: -0.1700
Data Index: 5134037 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19