Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3657. Min Range: -7.3657
Max Act: 7.3657. Min Act: -0.1700
Data Index: 1328390 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3657. Min Range: -7.3657
Max Act: 7.0845. Min Act: -0.1700
Data Index: 597413 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3657. Min Range: -7.3657
Max Act: 7.0532. Min Act: -0.1700
Data Index: 175693 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.9907. Min Act: -0.1700
Data Index: 2058221 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.9907. Min Act: -0.1700
Data Index: 7034656 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.9595. Min Act: -0.1700
Data Index: 4962978 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.9282. Min Act: -0.1700
Data Index: 7076200 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.9282. Min Act: -0.1700
Data Index: 6711350 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.9282. Min Act: -0.1700
Data Index: 6689998 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.8657. Min Act: -0.1700
Data Index: 576892 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.8657. Min Act: -0.1700
Data Index: 6608941 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.8345. Min Act: -0.1700
Data Index: 467441 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.8032. Min Act: -0.1700
Data Index: 7607232 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.7720. Min Act: -0.1700
Data Index: 4305322 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.7720. Min Act: -0.1700
Data Index: 1189230 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.7407. Min Act: -0.1700
Data Index: 3816009 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.7407. Min Act: -0.1700
Data Index: 5787803 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.7407. Min Act: -0.1700
Data Index: 5887325 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.7095. Min Act: -0.1700
Data Index: 3852895 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3657. Min Range: -7.3657
Max Act: 6.7095. Min Act: -0.1700
Data Index: 4471527 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19