Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1872. Min Range: -8.1872
Max Act: 8.1872. Min Act: -0.1700
Data Index: 2590686 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1872. Min Range: -8.1872
Max Act: 8.0934. Min Act: -0.1700
Data Index: 5601501 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.9997. Min Act: -0.1700
Data Index: 6074775 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.9372. Min Act: -0.1700
Data Index: 583250 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.9372. Min Act: -0.1700
Data Index: 5296769 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.9059. Min Act: -0.1700
Data Index: 7201764 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.8747. Min Act: -0.1700
Data Index: 1788352 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.8747. Min Act: -0.1700
Data Index: 5472717 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.7497. Min Act: -0.1700
Data Index: 1694380 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.6872. Min Act: -0.1700
Data Index: 1138959 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.6559. Min Act: -0.1700
Data Index: 4201783 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.6559. Min Act: -0.1700
Data Index: 2322591 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.6247. Min Act: -0.1700
Data Index: 3807579 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.5934. Min Act: -0.1700
Data Index: 6300913 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.5934. Min Act: -0.1700
Data Index: 6782589 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.5309. Min Act: -0.1700
Data Index: 6291142 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.5309. Min Act: -0.1700
Data Index: 1666559 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.5309. Min Act: -0.1700
Data Index: 4844457 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.4684. Min Act: -0.1700
Data Index: 3275754 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1872. Min Range: -8.1872
Max Act: 7.4684. Min Act: -0.1700
Data Index: 7171977 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19