Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.8006. Min Act: -0.1700
Data Index: 7749524 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.8006. Min Act: -0.1700
Data Index: 5012423 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.7381. Min Act: -0.1700
Data Index: 5303238 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.5506. Min Act: -0.1700
Data Index: 2412290 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.5194. Min Act: -0.1700
Data Index: 7751292 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.5194. Min Act: -0.1700
Data Index: 696889 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.2694. Min Act: -0.1700
Data Index: 3848314 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.2694. Min Act: -0.1700
Data Index: 3191662 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.1444. Min Act: -0.1700
Data Index: 2977762 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.0819. Min Act: -0.1700
Data Index: 214702 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.0819. Min Act: -0.1700
Data Index: 334341 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.0819. Min Act: -0.1700
Data Index: 1168374 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.0194. Min Act: -0.1700
Data Index: 6918793 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8006. Min Range: -6.8006
Max Act: 6.0194. Min Act: -0.1700
Data Index: 1874185 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8006. Min Range: -6.8006
Max Act: 5.9881. Min Act: -0.1700
Data Index: 6641950 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8006. Min Range: -6.8006
Max Act: 5.9569. Min Act: -0.1700
Data Index: 4888345 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8006. Min Range: -6.8006
Max Act: 5.9569. Min Act: -0.1700
Data Index: 1732898 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8006. Min Range: -6.8006
Max Act: 5.8944. Min Act: -0.1700
Data Index: 3646426 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8006. Min Range: -6.8006
Max Act: 5.8944. Min Act: -0.1700
Data Index: 7189915 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8006. Min Range: -6.8006
Max Act: 5.8944. Min Act: -0.1700
Data Index: 1686894 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19