Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9121. Min Range: -8.9121
Max Act: 8.9121. Min Act: -0.1700
Data Index: 198169 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.8496. Min Act: -0.1700
Data Index: 5376932 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.8496. Min Act: -0.1700
Data Index: 801552 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.6933. Min Act: -0.1700
Data Index: 6116296 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.5996. Min Act: -0.1700
Data Index: 4925996 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.5683. Min Act: -0.1700
Data Index: 7017763 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.5058. Min Act: -0.1700
Data Index: 119761 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.5058. Min Act: -0.1700
Data Index: 5721592 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.5058. Min Act: -0.1700
Data Index: 7076725 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.4746. Min Act: -0.1700
Data Index: 6370396 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.4433. Min Act: -0.1700
Data Index: 4652979 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.4433. Min Act: -0.1700
Data Index: 3413249 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.3808. Min Act: -0.1700
Data Index: 881601 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.4433. Min Act: -0.1700
Data Index: 4533155 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.4121. Min Act: -0.1700
Data Index: 5252095 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.3808. Min Act: -0.1700
Data Index: 6168667 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.3183. Min Act: -0.1700
Data Index: 4101017 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.3808. Min Act: -0.1700
Data Index: 4634169 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.3496. Min Act: -0.1700
Data Index: 3570949 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9121. Min Range: -8.9121
Max Act: 7.3496. Min Act: -0.1700
Data Index: 6484986 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19