Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 942 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.4212. Min Act: -0.1700
Data Index: 2636136 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.3231. Min Act: -0.1700
Data Index: 4740858 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.3231. Min Act: -0.1700
Data Index: 131357 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.3231. Min Act: -0.1700
Data Index: 6866255 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.3558. Min Act: -0.1700
Data Index: 6139146 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.2902. Min Act: -0.1700
Data Index: 264268 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.2075. Min Act: -0.1700
Data Index: 7125990 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1910. Min Act: -0.1700
Data Index: 3649429 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1743. Min Act: -0.1700
Data Index: 6150222 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1910. Min Act: -0.1700
Data Index: 8075946 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1743. Min Act: -0.1700
Data Index: 3954710 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1410. Min Act: -0.1700
Data Index: 5137973 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1410. Min Act: -0.1700
Data Index: 971739 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1410. Min Act: -0.1700
Data Index: 5706803 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1577. Min Act: -0.1700
Data Index: 3225092 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1076. Min Act: -0.1700
Data Index: 3187136 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1243. Min Act: -0.1700
Data Index: 4868644 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1076. Min Act: -0.1700
Data Index: 1823396 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.1076. Min Act: -0.1700
Data Index: 2307309 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4212. Min Range: -2.4212
Max Act: 2.0909. Min Act: -0.1700
Data Index: 1246951 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19