Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2373 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3408. Min Range: -8.3408
Max Act: 8.3408. Min Act: -0.1700
Data Index: 4024778 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3408. Min Range: -8.3408
Max Act: 8.2783. Min Act: -0.1700
Data Index: 4413293 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3408. Min Range: -8.3408
Max Act: 8.0283. Min Act: -0.1700
Data Index: 6008823 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3408. Min Range: -8.3408
Max Act: 8.0283. Min Act: -0.1700
Data Index: 5027475 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.9033. Min Act: -0.1700
Data Index: 7278771 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.8408. Min Act: -0.1700
Data Index: 4207674 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.7783. Min Act: -0.1700
Data Index: 5238001 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.7783. Min Act: -0.1700
Data Index: 1178218 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.7783. Min Act: -0.1700
Data Index: 6503235 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.7783. Min Act: -0.1700
Data Index: 2413092 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.7158. Min Act: -0.1700
Data Index: 5428635 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.7158. Min Act: -0.1700
Data Index: 8029302 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.6533. Min Act: -0.1700
Data Index: 4191087 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.6533. Min Act: -0.1700
Data Index: 8700032 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.5908. Min Act: -0.1700
Data Index: 5605007 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.5908. Min Act: -0.1700
Data Index: 5738016 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.5908. Min Act: -0.1700
Data Index: 3929543 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.5596. Min Act: -0.1700
Data Index: 2326085 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.5596. Min Act: -0.1700
Data Index: 2914888 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3408. Min Range: -8.3408
Max Act: 7.5283. Min Act: -0.1700
Data Index: 2060488 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19