Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2274 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.4049. Min Act: -0.1700
Data Index: 998822 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.3873. Min Act: -0.1700
Data Index: 8467570 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.3344. Min Act: -0.1698
Data Index: 8193576 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2991. Min Act: -0.1700
Data Index: 1528711 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2815. Min Act: -0.1700
Data Index: 6369979 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2815. Min Act: -0.1697
Data Index: 2839476 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2638. Min Act: -0.1698
Data Index: 2467661 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2462. Min Act: -0.1700
Data Index: 8597635 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2286. Min Act: -0.1700
Data Index: 5338159 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.2286. Min Act: -0.1700
Data Index: 4927017 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1933. Min Act: -0.1700
Data Index: 8807889 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1933. Min Act: -0.1700
Data Index: 5466349 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1933. Min Act: -0.1700
Data Index: 3783927 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1933. Min Act: -0.1700
Data Index: 8810970 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1700
Data Index: 8422025 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1699
Data Index: 550450 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1694
Data Index: 742389 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1700
Data Index: 3062537 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1757. Min Act: -0.1700
Data Index: 1951536 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4049. Min Range: -1.4049
Max Act: 1.1581. Min Act: -0.1700
Data Index: 5217170 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19