Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.7707. Min Act: -0.1700
Data Index: 5394882 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.7707. Min Act: -0.1700
Data Index: 7456890 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.5207. Min Act: -0.1700
Data Index: 1937024 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.4582. Min Act: -0.1700
Data Index: 1223945 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.4582. Min Act: -0.1700
Data Index: 4920151 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.2707. Min Act: -0.1700
Data Index: 2365343 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.2707. Min Act: -0.1700
Data Index: 117364 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.2082. Min Act: -0.1700
Data Index: 7023950 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.2082. Min Act: -0.1700
Data Index: 6093656 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.2082. Min Act: -0.1700
Data Index: 5763914 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.1457. Min Act: -0.1700
Data Index: 8825336 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.1457. Min Act: -0.1700
Data Index: 3615947 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.1457. Min Act: -0.1700
Data Index: 6136871 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.2082. Min Act: -0.1700
Data Index: 6951905 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.0832. Min Act: -0.1700
Data Index: 2770592 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.0832. Min Act: -0.1700
Data Index: 5108357 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.0832. Min Act: -0.1700
Data Index: 5394883 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.0832. Min Act: -0.1700
Data Index: 7538038 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7707. Min Range: -10.7707
Max Act: 10.0832. Min Act: -0.1700
Data Index: 8798233 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7707. Min Range: -10.7707
Max Act: 9.9582. Min Act: -0.1700
Data Index: 3100608 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19