Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0745. Min Range: -6.0745
Max Act: 6.0432. Min Act: -0.1700
Data Index: 1607749 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0745. Min Range: -6.0745
Max Act: 6.0745. Min Act: -0.1700
Data Index: 3274785 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0745. Min Range: -6.0745
Max Act: 6.0432. Min Act: -0.1700
Data Index: 2102233 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0745. Min Range: -6.0745
Max Act: 6.0120. Min Act: -0.1700
Data Index: 5230057 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.9495. Min Act: -0.1700
Data Index: 563197 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.9495. Min Act: -0.1700
Data Index: 7692393 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8870. Min Act: -0.1700
Data Index: 4644946 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.9182. Min Act: -0.1700
Data Index: 509032 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8870. Min Act: -0.1700
Data Index: 613273 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8557. Min Act: -0.1700
Data Index: 1297744 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8557. Min Act: -0.1700
Data Index: 8400878 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8557. Min Act: -0.1700
Data Index: 172685 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8245. Min Act: -0.1700
Data Index: 3856864 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8245. Min Act: -0.1700
Data Index: 3277438 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8245. Min Act: -0.1700
Data Index: 1075192 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.8245. Min Act: -0.1700
Data Index: 6748663 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.7932. Min Act: -0.1700
Data Index: 1636708 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.7932. Min Act: -0.1700
Data Index: 5115267 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.7932. Min Act: -0.1700
Data Index: 3240056 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0745. Min Range: -6.0745
Max Act: 5.7932. Min Act: -0.1700
Data Index: 6045818 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19