Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5387 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.1754. Min Act: -0.1700
Data Index: 3836552 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.1754. Min Act: -0.1688
Data Index: 3657094 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.1227. Min Act: -0.1699
Data Index: 6774137 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.1227. Min Act: -0.1700
Data Index: 2423148 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0877. Min Act: -0.1700
Data Index: 4532097 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0702. Min Act: -0.1700
Data Index: 3544657 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0702. Min Act: -0.1700
Data Index: 3335531 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0614. Min Act: -0.1700
Data Index: 7707074 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0702. Min Act: -0.1700
Data Index: 707541 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0266. Min Act: -0.1699
Data Index: 6735058 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0179. Min Act: -0.1698
Data Index: 7898665 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0266. Min Act: -0.1693
Data Index: 8708201 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0266. Min Act: -0.1700
Data Index: 8162713 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0092. Min Act: -0.1700
Data Index: 8126123 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1754. Min Range: -1.1754
Max Act: 1.0005. Min Act: -0.1700
Data Index: 5562994 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1754. Min Range: -1.1754
Max Act: 0.9918. Min Act: -0.1700
Data Index: 4226758 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1754. Min Range: -1.1754
Max Act: 0.9918. Min Act: -0.1690
Data Index: 7494903 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1754. Min Range: -1.1754
Max Act: 0.9918. Min Act: -0.1700
Data Index: 1263905 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1754. Min Range: -1.1754
Max Act: 0.9659. Min Act: -0.1700
Data Index: 6152723 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1754. Min Range: -1.1754
Max Act: 0.9572. Min Act: -0.1699
Data Index: 1310100 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19