Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4356 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.6252. Min Act: -0.1700
Data Index: 7303864 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.5627. Min Act: -0.1700
Data Index: 108102 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.5002. Min Act: -0.1700
Data Index: 3043866 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.3127. Min Act: -0.1700
Data Index: 394114 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.3127. Min Act: -0.1700
Data Index: 953364 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.2502. Min Act: -0.1700
Data Index: 1589771 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.1877. Min Act: -0.1700
Data Index: 8618170 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.1877. Min Act: -0.1700
Data Index: 3884540 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.0627. Min Act: -0.1700
Data Index: 783736 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.0315. Min Act: -0.1700
Data Index: 4267265 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.0002. Min Act: -0.1700
Data Index: 7692221 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.0315. Min Act: -0.1700
Data Index: 6694279 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6252. Min Range: -8.6252
Max Act: 8.0002. Min Act: -0.1700
Data Index: 7347905 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6252. Min Range: -8.6252
Max Act: 7.9690. Min Act: -0.1700
Data Index: 4348700 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6252. Min Range: -8.6252
Max Act: 7.9377. Min Act: -0.1700
Data Index: 5880884 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6252. Min Range: -8.6252
Max Act: 7.9065. Min Act: -0.1700
Data Index: 6200919 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6252. Min Range: -8.6252
Max Act: 7.8752. Min Act: -0.1700
Data Index: 1298927 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6252. Min Range: -8.6252
Max Act: 7.8752. Min Act: -0.1700
Data Index: 1913210 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6252. Min Range: -8.6252
Max Act: 7.9065. Min Act: -0.1700
Data Index: 8723442 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6252. Min Range: -8.6252
Max Act: 7.8440. Min Act: -0.1700
Data Index: 5804366 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19