Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2486. Min Range: -8.2486
Max Act: 8.2486. Min Act: -0.1700
Data Index: 5064166 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.9361. Min Act: -0.1700
Data Index: 4123780 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.9049. Min Act: -0.1700
Data Index: 5616803 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.7799. Min Act: -0.1700
Data Index: 388991 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.8111. Min Act: -0.1700
Data Index: 455304 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.7799. Min Act: -0.1700
Data Index: 13623 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.7486. Min Act: -0.1700
Data Index: 40877 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.7486. Min Act: -0.1700
Data Index: 2086334 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.6549. Min Act: -0.1700
Data Index: 267287 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.6236. Min Act: -0.1700
Data Index: 6798008 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.5924. Min Act: -0.1700
Data Index: 4569866 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.5611. Min Act: -0.1700
Data Index: 5208726 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.5611. Min Act: -0.1700
Data Index: 7084723 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.5299. Min Act: -0.1700
Data Index: 2540289 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.5299. Min Act: -0.1700
Data Index: 1958536 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.4986. Min Act: -0.1700
Data Index: 7468821 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.4986. Min Act: -0.1700
Data Index: 2501276 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.4986. Min Act: -0.1700
Data Index: 6160404 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.4986. Min Act: -0.1700
Data Index: 888695 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2486. Min Range: -8.2486
Max Act: 7.4986. Min Act: -0.1700
Data Index: 7733682 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19