Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 519 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.8267. Min Act: -0.1700
Data Index: 6443290 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.7017. Min Act: -0.1700
Data Index: 1867241 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.5767. Min Act: -0.1700
Data Index: 2034916 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.5142. Min Act: -0.1700
Data Index: 8543267 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.4829. Min Act: -0.1700
Data Index: 6162702 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.4829. Min Act: -0.1700
Data Index: 4379981 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.4204. Min Act: -0.1700
Data Index: 6122222 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.4204. Min Act: -0.1700
Data Index: 5145820 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3892. Min Act: -0.1700
Data Index: 151354 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3892. Min Act: -0.1700
Data Index: 5811689 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3892. Min Act: -0.1700
Data Index: 8077411 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3892. Min Act: -0.1700
Data Index: 7448588 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3579. Min Act: -0.1700
Data Index: 8178759 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3267. Min Act: -0.1700
Data Index: 316594 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3267. Min Act: -0.1700
Data Index: 7960325 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3267. Min Act: -0.1700
Data Index: 89545 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3267. Min Act: -0.1700
Data Index: 4256119 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.3267. Min Act: -0.1700
Data Index: 3913368 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.2954. Min Act: -0.1700
Data Index: 5884494 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8267. Min Range: -4.8267
Max Act: 4.2641. Min Act: -0.1700
Data Index: 2200076 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19