Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 782 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.4077. Min Range: -16.4077
Max Act: 16.4077. Min Act: -0.1700
Data Index: 1693691 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.4077. Min Range: -16.4077
Max Act: 16.2827. Min Act: -0.1700
Data Index: 1693690 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.7827. Min Act: -0.1700
Data Index: 8279284 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.7827. Min Act: -0.1700
Data Index: 7841919 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.5952. Min Act: -0.1700
Data Index: 7841922 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.5327. Min Act: -0.1700
Data Index: 7841921 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.4077. Min Act: -0.1700
Data Index: 5840060 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.2827. Min Act: -0.1700
Data Index: 7841920 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.2202. Min Act: -0.1700
Data Index: 7801194 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.2827. Min Act: -0.1700
Data Index: 7841926 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.2827. Min Act: -0.1700
Data Index: 3763123 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.2202. Min Act: -0.1700
Data Index: 3735484 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.0952. Min Act: -0.1700
Data Index: 85610 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.1577. Min Act: -0.1700
Data Index: 5707385 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.0952. Min Act: -0.1700
Data Index: 5161341 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.0952. Min Act: -0.1700
Data Index: 1590298 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.0327. Min Act: -0.1700
Data Index: 851165 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.0327. Min Act: -0.1700
Data Index: 6439653 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.4077. Min Range: -16.4077
Max Act: 15.0327. Min Act: -0.1700
Data Index: 8108836 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.4077. Min Range: -16.4077
Max Act: 14.9702. Min Act: -0.1700
Data Index: 7885676 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19