Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 1083932 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 7194723 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 7471661 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 924573 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 7162103 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 7092621 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 6789460 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 5904166 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 5659052 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 5071323 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 4803096 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 4793556 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 4750174 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 3519494 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 3434610 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 2956792 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 2923265 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 2020061 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 1795111 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2697. Min Range: -8.2697
Max Act: 8.2697. Min Act: -0.1700
Data Index: 1299312 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19