Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2723 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3754. Min Range: -10.3754
Max Act: 10.3754. Min Act: -0.1700
Data Index: 4845051 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3754. Min Range: -10.3754
Max Act: 10.1254. Min Act: -0.1700
Data Index: 3212872 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3754. Min Range: -10.3754
Max Act: 10.1254. Min Act: -0.1700
Data Index: 5313472 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3754. Min Range: -10.3754
Max Act: 10.0629. Min Act: -0.1700
Data Index: 1538710 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3754. Min Range: -10.3754
Max Act: 10.0004. Min Act: -0.1700
Data Index: 8645588 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.9379. Min Act: -0.1700
Data Index: 7084298 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.9379. Min Act: -0.1700
Data Index: 8166865 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.9379. Min Act: -0.1700
Data Index: 1882826 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.8129. Min Act: -0.1700
Data Index: 5936418 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.7504. Min Act: -0.1700
Data Index: 4358861 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.6879. Min Act: -0.1700
Data Index: 2853053 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.6254. Min Act: -0.1700
Data Index: 4952777 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.6254. Min Act: -0.1700
Data Index: 454008 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.5004. Min Act: -0.1700
Data Index: 4021830 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.4379. Min Act: -0.1700
Data Index: 681940 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.4379. Min Act: -0.1700
Data Index: 5052187 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.4379. Min Act: -0.1700
Data Index: 6300390 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.3754. Min Act: -0.1700
Data Index: 661118 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.3129. Min Act: -0.1700
Data Index: 744966 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3754. Min Range: -10.3754
Max Act: 9.2504. Min Act: -0.1700
Data Index: 2995569 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19