Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.2245. Min Act: -0.1700
Data Index: 6648676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.2069. Min Act: -0.1700
Data Index: 5219336 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1805. Min Act: -0.1700
Data Index: 4015098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1717. Min Act: -0.1700
Data Index: 1368389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1805. Min Act: -0.1700
Data Index: 2741749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1541. Min Act: -0.1700
Data Index: 5884843 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1541. Min Act: -0.1700
Data Index: 2660028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1700
Data Index: 855194 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1541. Min Act: -0.1700
Data Index: 1249590 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1541. Min Act: -0.1697
Data Index: 5284052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1541. Min Act: -0.1699
Data Index: 3689662 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1696
Data Index: 1439814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1365. Min Act: -0.1700
Data Index: 7820952 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1698
Data Index: 2232114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1700
Data Index: 108564 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1699
Data Index: 2944640 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1700
Data Index: 7122764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1700
Data Index: 2731405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1700
Data Index: 7451423 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2245. Min Range: -1.2245
Max Act: 1.1453. Min Act: -0.1700
Data Index: 1199264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19