Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2727 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.6870. Min Act: -0.1700
Data Index: 1764267 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.6870. Min Act: -0.1700
Data Index: 3560077 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.4370. Min Act: -0.1700
Data Index: 5612249 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.2495. Min Act: -0.1700
Data Index: 6175895 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.1870. Min Act: -0.1700
Data Index: 4816818 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.1870. Min Act: -0.1700
Data Index: 1257917 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.1558. Min Act: -0.1700
Data Index: 3064199 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.0933. Min Act: -0.1700
Data Index: 2253691 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6870. Min Range: -8.6870
Max Act: 8.0620. Min Act: -0.1700
Data Index: 180976 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9995. Min Act: -0.1700
Data Index: 659731 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9683. Min Act: -0.1700
Data Index: 1390283 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9683. Min Act: -0.1700
Data Index: 7398372 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9370. Min Act: -0.1700
Data Index: 3256105 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9058. Min Act: -0.1700
Data Index: 7187526 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9058. Min Act: -0.1700
Data Index: 3765362 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9058. Min Act: -0.1700
Data Index: 7788173 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9370. Min Act: -0.1700
Data Index: 1433172 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.9058. Min Act: -0.1700
Data Index: 4352767 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.8745. Min Act: -0.1700
Data Index: 6338287 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6870. Min Range: -8.6870
Max Act: 7.8120. Min Act: -0.1700
Data Index: 6593920 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19