Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.6777. Min Act: -0.1700
Data Index: 4394697 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.6465. Min Act: -0.1700
Data Index: 4063680 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.6465. Min Act: -0.1700
Data Index: 7027660 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.6152. Min Act: -0.1700
Data Index: 97045 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.6465. Min Act: -0.1700
Data Index: 1813639 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5840. Min Act: -0.1700
Data Index: 8335631 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5840. Min Act: -0.1700
Data Index: 2962474 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5840. Min Act: -0.1700
Data Index: 1904578 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5527. Min Act: -0.1700
Data Index: 500686 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5840. Min Act: -0.1700
Data Index: 1804865 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5527. Min Act: -0.1700
Data Index: 379111 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5527. Min Act: -0.1700
Data Index: 4850263 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5215. Min Act: -0.1700
Data Index: 6504165 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5215. Min Act: -0.1700
Data Index: 2867332 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5215. Min Act: -0.1700
Data Index: 82113 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5215. Min Act: -0.1700
Data Index: 8829562 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5215. Min Act: -0.1700
Data Index: 8686861 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5215. Min Act: -0.1700
Data Index: 1303687 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5527. Min Act: -0.1700
Data Index: 1908621 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6777. Min Range: -4.6777
Max Act: 4.5215. Min Act: -0.1700
Data Index: 4479051 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19