Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4380 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.8267. Min Act: -0.1700
Data Index: 5574304 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.7642. Min Act: -0.1700
Data Index: 927017 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.7642. Min Act: -0.1700
Data Index: 927016 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5455. Min Act: -0.1700
Data Index: 1517375 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5455. Min Act: -0.1700
Data Index: 2670172 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.5142. Min Act: -0.1700
Data Index: 6182333 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4830. Min Act: -0.1700
Data Index: 1215191 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4830. Min Act: -0.1700
Data Index: 8721424 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4517. Min Act: -0.1700
Data Index: 1169084 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4205. Min Act: -0.1700
Data Index: 4106160 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4517. Min Act: -0.1700
Data Index: 7145144 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4830. Min Act: -0.1700
Data Index: 3347421 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4517. Min Act: -0.1700
Data Index: 7514140 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4205. Min Act: -0.1700
Data Index: 3084249 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4205. Min Act: -0.1700
Data Index: 4836501 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.3892. Min Act: -0.1700
Data Index: 2796907 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1011839 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.3892. Min Act: -0.1700
Data Index: 5972624 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.3580. Min Act: -0.1700
Data Index: 2029708 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.3267. Min Act: -0.1700
Data Index: 1553593 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19