Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2356 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1851. Min Range: -6.1851
Max Act: 6.1851. Min Act: -0.1700
Data Index: 2458262 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1851. Min Range: -6.1851
Max Act: 6.0913. Min Act: -0.1700
Data Index: 3923980 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1851. Min Range: -6.1851
Max Act: 6.1226. Min Act: -0.1700
Data Index: 6378528 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1851. Min Range: -6.1851
Max Act: 6.0288. Min Act: -0.1700
Data Index: 4856367 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.9976. Min Act: -0.1700
Data Index: 6275377 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.9976. Min Act: -0.1700
Data Index: 7847560 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.9351. Min Act: -0.1700
Data Index: 2384387 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.9351. Min Act: -0.1700
Data Index: 3794826 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.7788. Min Act: -0.1700
Data Index: 7246606 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.7788. Min Act: -0.1700
Data Index: 5011112 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.6851. Min Act: -0.1700
Data Index: 796909 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.6851. Min Act: -0.1700
Data Index: 3704858 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.6851. Min Act: -0.1700
Data Index: 1669567 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.6226. Min Act: -0.1700
Data Index: 4279031 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.6226. Min Act: -0.1700
Data Index: 8551445 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.5913. Min Act: -0.1700
Data Index: 8742780 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.5601. Min Act: -0.1700
Data Index: 7760413 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.4976. Min Act: -0.1700
Data Index: 2816220 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.4976. Min Act: -0.1700
Data Index: 3465646 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1851. Min Range: -6.1851
Max Act: 5.4976. Min Act: -0.1700
Data Index: 762215 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19