Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.3141. Min Act: -0.1700
Data Index: 6071152 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.2516. Min Act: -0.1700
Data Index: 6506452 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.2203. Min Act: -0.1700
Data Index: 5193888 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.1266. Min Act: -0.1700
Data Index: 4119755 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.1266. Min Act: -0.1700
Data Index: 5963889 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.1266. Min Act: -0.1700
Data Index: 8509693 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.0953. Min Act: -0.1700
Data Index: 7488486 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.0641. Min Act: -0.1700
Data Index: 6697237 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.0641. Min Act: -0.1700
Data Index: 5045893 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.0328. Min Act: -0.1700
Data Index: 3797105 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.0015. Min Act: -0.1700
Data Index: 1315240 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.0015. Min Act: -0.1700
Data Index: 2438837 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3141. Min Range: -4.3141
Max Act: 3.9703. Min Act: -0.1700
Data Index: 718225 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3141. Min Range: -4.3141
Max Act: 4.0015. Min Act: -0.1700
Data Index: 6883853 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3141. Min Range: -4.3141
Max Act: 3.9390. Min Act: -0.1700
Data Index: 8038066 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3141. Min Range: -4.3141
Max Act: 3.9077. Min Act: -0.1700
Data Index: 1618394 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3141. Min Range: -4.3141
Max Act: 3.9390. Min Act: -0.1700
Data Index: 4659628 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3141. Min Range: -4.3141
Max Act: 3.9390. Min Act: -0.1700
Data Index: 4526737 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3141. Min Range: -4.3141
Max Act: 3.9390. Min Act: -0.1700
Data Index: 5749243 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3141. Min Range: -4.3141
Max Act: 3.9390. Min Act: -0.1700
Data Index: 6853607 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19