Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2400. Min Range: -6.2400
Max Act: 6.2400. Min Act: -0.1700
Data Index: 2077902 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.8650. Min Act: -0.1700
Data Index: 943466 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.8025. Min Act: -0.1700
Data Index: 8340549 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.8025. Min Act: -0.1700
Data Index: 3137440 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.7712. Min Act: -0.1700
Data Index: 64261 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.7400. Min Act: -0.1700
Data Index: 7091236 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.7400. Min Act: -0.1700
Data Index: 923740 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.7400. Min Act: -0.1700
Data Index: 6960112 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.7087. Min Act: -0.1700
Data Index: 3991207 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.7087. Min Act: -0.1700
Data Index: 3546466 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.7087. Min Act: -0.1700
Data Index: 69715 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6775. Min Act: -0.1700
Data Index: 6343425 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6775. Min Act: -0.1700
Data Index: 5678289 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6462. Min Act: -0.1700
Data Index: 4349963 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2668483 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2351346 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6462. Min Act: -0.1700
Data Index: 6444219 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6462. Min Act: -0.1700
Data Index: 6312331 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6462. Min Act: -0.1700
Data Index: 2387030 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2400. Min Range: -6.2400
Max Act: 5.6462. Min Act: -0.1700
Data Index: 3329951 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19