Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5175 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.8160. Min Act: -0.1700
Data Index: 2645144 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.5660. Min Act: -0.1700
Data Index: 7049004 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.4097. Min Act: -0.1700
Data Index: 3606842 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.4097. Min Act: -0.1700
Data Index: 4667222 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.3785. Min Act: -0.1700
Data Index: 429799 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.3785. Min Act: -0.1700
Data Index: 2950772 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.3472. Min Act: -0.1700
Data Index: 2039316 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.2847. Min Act: -0.1700
Data Index: 7026894 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.2222. Min Act: -0.1700
Data Index: 7930369 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.2222. Min Act: -0.1700
Data Index: 8705500 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.2222. Min Act: -0.1700
Data Index: 6062291 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1910. Min Act: -0.1700
Data Index: 2898308 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1597. Min Act: -0.1700
Data Index: 2525194 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1597. Min Act: -0.1700
Data Index: 7621392 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1597. Min Act: -0.1700
Data Index: 381663 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1597. Min Act: -0.1700
Data Index: 4013653 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1597. Min Act: -0.1700
Data Index: 2950305 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1597. Min Act: -0.1700
Data Index: 4093668 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1285. Min Act: -0.1700
Data Index: 4249932 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8160. Min Range: -6.8160
Max Act: 6.1285. Min Act: -0.1700
Data Index: 2938967 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19