Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5521 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.3870. Min Act: -0.1700
Data Index: 5245608 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.3870. Min Act: -0.1700
Data Index: 1337997 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.3245. Min Act: -0.1700
Data Index: 2184179 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.2933. Min Act: -0.1700
Data Index: 8076243 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.2308. Min Act: -0.1700
Data Index: 7420829 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.2308. Min Act: -0.1700
Data Index: 6159733 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.2308. Min Act: -0.1700
Data Index: 3099839 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.2308. Min Act: -0.1700
Data Index: 1340308 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1683. Min Act: -0.1700
Data Index: 7392334 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.2308. Min Act: -0.1700
Data Index: 7982870 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1995. Min Act: -0.1700
Data Index: 7012648 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1995. Min Act: -0.1700
Data Index: 4385686 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1995. Min Act: -0.1700
Data Index: 5938541 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1995. Min Act: -0.1700
Data Index: 6461505 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1683. Min Act: -0.1700
Data Index: 614907 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1058. Min Act: -0.1700
Data Index: 7391155 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1370. Min Act: -0.1700
Data Index: 2673690 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1370. Min Act: -0.1700
Data Index: 1317285 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1370. Min Act: -0.1700
Data Index: 3101491 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3870. Min Range: -5.3870
Max Act: 5.1058. Min Act: -0.1700
Data Index: 7907423 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19