Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.5057. Min Act: -0.1700
Data Index: 3387596 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.1307. Min Act: -0.1700
Data Index: 7335536 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.1307. Min Act: -0.1700
Data Index: 6676282 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.0994. Min Act: -0.1700
Data Index: 3077736 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9744. Min Act: -0.1700
Data Index: 4421249 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9744. Min Act: -0.1700
Data Index: 249733 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9744. Min Act: -0.1700
Data Index: 3585653 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5057. Min Range: -5.5057
Max Act: 5.0057. Min Act: -0.1700
Data Index: 4216976 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.9119. Min Act: -0.1700
Data Index: 5694398 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 6961515 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8807. Min Act: -0.1700
Data Index: 3370266 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8807. Min Act: -0.1700
Data Index: 913972 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 8303428 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 3048816 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 385903 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 8607284 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 4524479 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8494. Min Act: -0.1700
Data Index: 7320181 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8807. Min Act: -0.1700
Data Index: 2857282 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5057. Min Range: -5.5057
Max Act: 4.8182. Min Act: -0.1700
Data Index: 3988025 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19