Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.9704. Min Act: -0.1700
Data Index: 3564145 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.7829. Min Act: -0.1700
Data Index: 7088345 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.6579. Min Act: -0.1700
Data Index: 7502854 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5954. Min Act: -0.1700
Data Index: 5741376 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5329. Min Act: -0.1700
Data Index: 5344177 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5329. Min Act: -0.1700
Data Index: 4178371 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.5017. Min Act: -0.1700
Data Index: 2347451 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.4392. Min Act: -0.1700
Data Index: 7146110 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.4392. Min Act: -0.1700
Data Index: 2831812 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.4079. Min Act: -0.1700
Data Index: 4229580 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.4079. Min Act: -0.1700
Data Index: 2005672 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.3767. Min Act: -0.1700
Data Index: 8517194 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.3454. Min Act: -0.1700
Data Index: 4229590 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.3454. Min Act: -0.1700
Data Index: 1723000 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.3767. Min Act: -0.1700
Data Index: 6786380 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.3767. Min Act: -0.1700
Data Index: 214295 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.3454. Min Act: -0.1700
Data Index: 3731368 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.3142. Min Act: -0.1700
Data Index: 6064523 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.2829. Min Act: -0.1700
Data Index: 4459497 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9704. Min Range: -5.9704
Max Act: 5.2829. Min Act: -0.1700
Data Index: 2477064 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19