Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.4251. Min Act: -0.1700
Data Index: 4335382 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4251. Min Range: -5.4251
Max Act: 5.0501. Min Act: -0.1700
Data Index: 4916350 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.9563. Min Act: -0.1700
Data Index: 650769 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.9251. Min Act: -0.1700
Data Index: 2281925 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.9251. Min Act: -0.1700
Data Index: 2334837 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.8938. Min Act: -0.1700
Data Index: 2696165 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.8313. Min Act: -0.1700
Data Index: 7171704 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.8001. Min Act: -0.1700
Data Index: 3617264 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.8313. Min Act: -0.1700
Data Index: 2438670 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.8001. Min Act: -0.1700
Data Index: 4839686 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.8001. Min Act: -0.1700
Data Index: 5644447 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7688. Min Act: -0.1700
Data Index: 7690635 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7688. Min Act: -0.1700
Data Index: 168803 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7688. Min Act: -0.1700
Data Index: 4401152 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7376. Min Act: -0.1700
Data Index: 3683176 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.8001. Min Act: -0.1700
Data Index: 2577756 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7688. Min Act: -0.1700
Data Index: 6911936 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7688. Min Act: -0.1700
Data Index: 5853735 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7376. Min Act: -0.1700
Data Index: 5643092 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4251. Min Range: -5.4251
Max Act: 4.7376. Min Act: -0.1700
Data Index: 2305313 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19