Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.3309. Min Act: -0.1700
Data Index: 4720845 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.2372. Min Act: -0.1700
Data Index: 7609049 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.2372. Min Act: -0.1700
Data Index: 5510078 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.2059. Min Act: -0.1700
Data Index: 5613888 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1747. Min Act: -0.1700
Data Index: 5159144 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1747. Min Act: -0.1700
Data Index: 4010979 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1434. Min Act: -0.1700
Data Index: 7742038 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1122. Min Act: -0.1700
Data Index: 6513177 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1434. Min Act: -0.1700
Data Index: 7646957 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1434. Min Act: -0.1700
Data Index: 5976970 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1434. Min Act: -0.1700
Data Index: 5035221 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1122. Min Act: -0.1700
Data Index: 5072299 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.0809. Min Act: -0.1700
Data Index: 2737646 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.0809. Min Act: -0.1700
Data Index: 2967874 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.0809. Min Act: -0.1700
Data Index: 1723275 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.0809. Min Act: -0.1700
Data Index: 829763 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.0809. Min Act: -0.1700
Data Index: 3196724 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.1122. Min Act: -0.1700
Data Index: 5278809 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.0497. Min Act: -0.1700
Data Index: 3519007 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3309. Min Range: -5.3309
Max Act: 5.0497. Min Act: -0.1700
Data Index: 1370534 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19