Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.8008. Min Act: -0.1700
Data Index: 2707791 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.4258. Min Act: -0.1700
Data Index: 7481553 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3945. Min Act: -0.1700
Data Index: 3194467 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3945. Min Act: -0.1700
Data Index: 4195684 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3633. Min Act: -0.1700
Data Index: 6722593 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3633. Min Act: -0.1700
Data Index: 6082519 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3320. Min Act: -0.1700
Data Index: 786863 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3320. Min Act: -0.1700
Data Index: 5719461 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3320. Min Act: -0.1700
Data Index: 2081735 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3320. Min Act: -0.1700
Data Index: 6926512 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.3008. Min Act: -0.1700
Data Index: 5308258 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.2695. Min Act: -0.1700
Data Index: 4564898 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.2383. Min Act: -0.1700
Data Index: 837029 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.2070. Min Act: -0.1700
Data Index: 7352389 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.1758. Min Act: -0.1700
Data Index: 3579291 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.1758. Min Act: -0.1700
Data Index: 5412319 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.2070. Min Act: -0.1700
Data Index: 2896920 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.1445. Min Act: -0.1700
Data Index: 5940277 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.1445. Min Act: -0.1700
Data Index: 4547918 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8008. Min Range: -7.8008
Max Act: 7.1445. Min Act: -0.1700
Data Index: 8140962 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19