Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3841 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.9858. Min Act: -0.1700
Data Index: 7950283 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.8608. Min Act: -0.1700
Data Index: 529654 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.8608. Min Act: -0.1700
Data Index: 1754787 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.7983. Min Act: -0.1700
Data Index: 8075981 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.7983. Min Act: -0.1700
Data Index: 2218218 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.7670. Min Act: -0.1700
Data Index: 1333103 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.7045. Min Act: -0.1700
Data Index: 6373004 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.6733. Min Act: -0.1700
Data Index: 2242722 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.6733. Min Act: -0.1700
Data Index: 5512903 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.6420. Min Act: -0.1700
Data Index: 4085414 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.6108. Min Act: -0.1700
Data Index: 3542503 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.5795. Min Act: -0.1700
Data Index: 3085923 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.6108. Min Act: -0.1700
Data Index: 6358167 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.5483. Min Act: -0.1700
Data Index: 568106 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.5483. Min Act: -0.1700
Data Index: 1333098 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.4858. Min Act: -0.1700
Data Index: 4109930 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.5170. Min Act: -0.1700
Data Index: 7298438 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.4545. Min Act: -0.1700
Data Index: 3099309 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.3920. Min Act: -0.1700
Data Index: 2572036 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9858. Min Range: -6.9858
Max Act: 6.3608. Min Act: -0.1700
Data Index: 3704462 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19