Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.7183. Min Act: -0.1700
Data Index: 5410991 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.6558. Min Act: -0.1700
Data Index: 4397505 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.4683. Min Act: -0.1700
Data Index: 7436678 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.4370. Min Act: -0.1700
Data Index: 7400904 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.4370. Min Act: -0.1700
Data Index: 4254808 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.3433. Min Act: -0.1700
Data Index: 5504219 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.3120. Min Act: -0.1700
Data Index: 4607034 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.2808. Min Act: -0.1700
Data Index: 5113526 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.2495. Min Act: -0.1700
Data Index: 3161496 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.2495. Min Act: -0.1700
Data Index: 2953058 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1870. Min Act: -0.1700
Data Index: 5085063 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1870. Min Act: -0.1700
Data Index: 5714860 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1558. Min Act: -0.1700
Data Index: 2242614 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1245. Min Act: -0.1700
Data Index: 3676591 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.0933. Min Act: -0.1700
Data Index: 5594454 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1245. Min Act: -0.1700
Data Index: 6999416 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1245. Min Act: -0.1700
Data Index: 1981978 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1245. Min Act: -0.1700
Data Index: 5537011 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1245. Min Act: -0.1700
Data Index: 4731224 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7183. Min Range: -6.7183
Max Act: 6.1245. Min Act: -0.1700
Data Index: 1213966 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19