Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3110. Min Range: -6.3110
Max Act: 6.3110. Min Act: -0.1700
Data Index: 5836452 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3110. Min Range: -6.3110
Max Act: 6.2173. Min Act: -0.1700
Data Index: 1336099 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3110. Min Range: -6.3110
Max Act: 6.0610. Min Act: -0.1700
Data Index: 3374124 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3110. Min Range: -6.3110
Max Act: 6.0298. Min Act: -0.1700
Data Index: 6518883 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.9673. Min Act: -0.1700
Data Index: 3340865 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.9048. Min Act: -0.1700
Data Index: 1911507 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.9048. Min Act: -0.1700
Data Index: 630371 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8735. Min Act: -0.1700
Data Index: 5200536 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8735. Min Act: -0.1700
Data Index: 4537343 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8423. Min Act: -0.1700
Data Index: 5096848 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 2238647 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 480408 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 7475869 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 698825 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.7798. Min Act: -0.1700
Data Index: 7939448 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.8110. Min Act: -0.1700
Data Index: 6442794 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.7798. Min Act: -0.1700
Data Index: 7462611 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.7798. Min Act: -0.1700
Data Index: 1122817 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.7798. Min Act: -0.1700
Data Index: 1802953 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3110. Min Range: -6.3110
Max Act: 5.7798. Min Act: -0.1700
Data Index: 6107133 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19