Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6370 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1750. Min Range: -7.1750
Max Act: 7.1750. Min Act: -0.1700
Data Index: 2008069 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1750. Min Range: -7.1750
Max Act: 7.1437. Min Act: -0.1700
Data Index: 2725471 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1750. Min Range: -7.1750
Max Act: 7.0812. Min Act: -0.1700
Data Index: 3123265 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1750. Min Range: -7.1750
Max Act: 7.0187. Min Act: -0.1700
Data Index: 2114814 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.9250. Min Act: -0.1700
Data Index: 7607268 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8625. Min Act: -0.1700
Data Index: 1378167 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8937. Min Act: -0.1700
Data Index: 4244186 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8937. Min Act: -0.1700
Data Index: 7607275 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8937. Min Act: -0.1700
Data Index: 3123253 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8312. Min Act: -0.1700
Data Index: 5544566 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8312. Min Act: -0.1700
Data Index: 2008075 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8625. Min Act: -0.1700
Data Index: 434431 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8625. Min Act: -0.1700
Data Index: 8805161 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8625. Min Act: -0.1700
Data Index: 2914343 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8625. Min Act: -0.1700
Data Index: 3906119 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8312. Min Act: -0.1700
Data Index: 8015211 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8312. Min Act: -0.1700
Data Index: 884189 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8312. Min Act: -0.1700
Data Index: 6804573 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.8000. Min Act: -0.1700
Data Index: 1605840 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1750. Min Range: -7.1750
Max Act: 6.7687. Min Act: -0.1700
Data Index: 1386869 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19