Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3794 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0759. Min Range: -9.0759
Max Act: 9.0759. Min Act: -0.1700
Data Index: 229381 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0759. Min Range: -9.0759
Max Act: 9.0134. Min Act: -0.1700
Data Index: 1960444 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.7634. Min Act: -0.1700
Data Index: 2354090 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.8259. Min Act: -0.1700
Data Index: 1665784 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.7634. Min Act: -0.1700
Data Index: 1259475 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.7634. Min Act: -0.1700
Data Index: 3665237 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.7634. Min Act: -0.1700
Data Index: 2209678 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.7009. Min Act: -0.1700
Data Index: 1317983 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.6384. Min Act: -0.1700
Data Index: 7027225 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.6384. Min Act: -0.1700
Data Index: 6827363 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.6384. Min Act: -0.1700
Data Index: 4814836 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.6384. Min Act: -0.1700
Data Index: 2601686 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.6384. Min Act: -0.1700
Data Index: 5761554 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.5759. Min Act: -0.1700
Data Index: 1103084 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.5759. Min Act: -0.1700
Data Index: 3033364 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.5134. Min Act: -0.1700
Data Index: 139702 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.5134. Min Act: -0.1700
Data Index: 610474 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.5134. Min Act: -0.1700
Data Index: 109373 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.5134. Min Act: -0.1700
Data Index: 755982 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0759. Min Range: -9.0759
Max Act: 8.5134. Min Act: -0.1700
Data Index: 2833049 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19