Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4484 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4010. Min Range: -7.4010
Max Act: 7.4010. Min Act: -0.1700
Data Index: 2946345 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4010. Min Range: -7.4010
Max Act: 7.3385. Min Act: -0.1700
Data Index: 5299720 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4010. Min Range: -7.4010
Max Act: 7.3072. Min Act: -0.1700
Data Index: 1342660 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4010. Min Range: -7.4010
Max Act: 7.0885. Min Act: -0.1700
Data Index: 6034003 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4010. Min Range: -7.4010
Max Act: 7.0885. Min Act: -0.1700
Data Index: 6054746 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4010. Min Range: -7.4010
Max Act: 7.0572. Min Act: -0.1700
Data Index: 858581 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4010. Min Range: -7.4010
Max Act: 7.0260. Min Act: -0.1700
Data Index: 1826412 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.9635. Min Act: -0.1700
Data Index: 5097678 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.9635. Min Act: -0.1700
Data Index: 4538490 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.9010. Min Act: -0.1700
Data Index: 4688605 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.9010. Min Act: -0.1700
Data Index: 2084541 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.8385. Min Act: -0.1700
Data Index: 2717927 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.8385. Min Act: -0.1700
Data Index: 2053345 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.8385. Min Act: -0.1700
Data Index: 5299725 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.8385. Min Act: -0.1700
Data Index: 4538491 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.8385. Min Act: -0.1700
Data Index: 2118898 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.7760. Min Act: -0.1700
Data Index: 3310300 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.8072. Min Act: -0.1700
Data Index: 4736956 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.7447. Min Act: -0.1700
Data Index: 5452239 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4010. Min Range: -7.4010
Max Act: 6.7760. Min Act: -0.1700
Data Index: 8233707 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19