Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5052 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.6268. Min Act: -0.1700
Data Index: 2727729 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.5018. Min Act: -0.1700
Data Index: 2727727 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.2831. Min Act: -0.1700
Data Index: 3155939 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.1268. Min Act: -0.1700
Data Index: 462754 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.0643. Min Act: -0.1700
Data Index: 3849468 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.0643. Min Act: -0.1700
Data Index: 2727714 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.0331. Min Act: -0.1700
Data Index: 2935832 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6268. Min Range: -6.6268
Max Act: 6.0018. Min Act: -0.1700
Data Index: 3155937 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9706. Min Act: -0.1700
Data Index: 3890943 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9706. Min Act: -0.1700
Data Index: 7385555 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9706. Min Act: -0.1700
Data Index: 3155938 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9393. Min Act: -0.1700
Data Index: 176619 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9393. Min Act: -0.1700
Data Index: 3155932 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9081. Min Act: -0.1700
Data Index: 4301109 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9081. Min Act: -0.1700
Data Index: 6049248 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.8768. Min Act: -0.1700
Data Index: 7123793 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9393. Min Act: -0.1700
Data Index: 4284520 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.9081. Min Act: -0.1700
Data Index: 7020901 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.8768. Min Act: -0.1700
Data Index: 462738 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6268. Min Range: -6.6268
Max Act: 5.8768. Min Act: -0.1700
Data Index: 6415908 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19