Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1378 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.6537. Min Act: -0.1700
Data Index: 4401864 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.4974. Min Act: -0.1700
Data Index: 1737131 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.4037. Min Act: -0.1700
Data Index: 7891861 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.4037. Min Act: -0.1700
Data Index: 2956789 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.4349. Min Act: -0.1700
Data Index: 2956787 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.4037. Min Act: -0.1700
Data Index: 234731 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.3724. Min Act: -0.1700
Data Index: 4457913 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.3099. Min Act: -0.1700
Data Index: 4350816 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.3412. Min Act: -0.1700
Data Index: 1777619 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.3099. Min Act: -0.1700
Data Index: 4862827 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.2474. Min Act: -0.1700
Data Index: 1715950 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.2474. Min Act: -0.1700
Data Index: 8627001 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.2162. Min Act: -0.1700
Data Index: 1794183 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.2162. Min Act: -0.1700
Data Index: 8519642 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.1849. Min Act: -0.1700
Data Index: 8585687 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.1537. Min Act: -0.1700
Data Index: 5890412 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.1537. Min Act: -0.1700
Data Index: 1496578 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.1537. Min Act: -0.1700
Data Index: 3369078 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.1224. Min Act: -0.1700
Data Index: 8013567 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6537. Min Range: -6.6537
Max Act: 6.1537. Min Act: -0.1700
Data Index: 2048604 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19