Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.5760. Min Act: -0.1700
Data Index: 2225197 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.2635. Min Act: -0.1699
Data Index: 6180009 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.2010. Min Act: -0.1700
Data Index: 6749714 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.1385. Min Act: -0.1700
Data Index: 7333216 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.1073. Min Act: -0.1700
Data Index: 2261376 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.1073. Min Act: -0.1700
Data Index: 4966836 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.1073. Min Act: -0.1700
Data Index: 2479356 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.0448. Min Act: -0.1700
Data Index: 5383599 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.0448. Min Act: -0.1700
Data Index: 2537405 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.0135. Min Act: -0.1700
Data Index: 8056829 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9823. Min Act: -0.1700
Data Index: 7160358 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5760. Min Range: -6.5760
Max Act: 6.0135. Min Act: -0.1700
Data Index: 4298440 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9823. Min Act: -0.1700
Data Index: 5845181 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9823. Min Act: -0.1700
Data Index: 3700709 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9198. Min Act: -0.1700
Data Index: 4359481 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9510. Min Act: -0.1700
Data Index: 2139785 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9823. Min Act: -0.1700
Data Index: 7646746 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9198. Min Act: -0.1700
Data Index: 887022 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9198. Min Act: -0.1700
Data Index: 3167467 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5760. Min Range: -6.5760
Max Act: 5.9198. Min Act: -0.1700
Data Index: 457857 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19