Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.7188. Min Act: -0.1677
Data Index: 2362533 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.7106. Min Act: -0.1684
Data Index: 1784876 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.6780. Min Act: -0.1700
Data Index: 2722843 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.6218. Min Act: -0.1700
Data Index: 4737780 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.6218. Min Act: -0.1700
Data Index: 5836845 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.6139. Min Act: -0.1700
Data Index: 1404774 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.6139. Min Act: -0.1700
Data Index: 2662236 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5903. Min Act: -0.1700
Data Index: 549602 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5903. Min Act: -0.1700
Data Index: 4468397 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5903. Min Act: -0.1694
Data Index: 4383824 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5747. Min Act: -0.1700
Data Index: 142757 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5825. Min Act: -0.1685
Data Index: 499126 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5747. Min Act: -0.1700
Data Index: 1921644 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5747. Min Act: -0.1698
Data Index: 2362532 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5591. Min Act: -0.1698
Data Index: 7752899 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5591. Min Act: -0.1698
Data Index: 3116974 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5514. Min Act: -0.1700
Data Index: 8173131 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5591. Min Act: -0.1698
Data Index: 5209584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5591. Min Act: -0.1700
Data Index: 142756 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7188. Min Range: -0.7188
Max Act: 0.5591. Min Act: -0.1700
Data Index: 5173593 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19