Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5024 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.7294. Min Act: -0.1700
Data Index: 7625620 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.6044. Min Act: -0.1700
Data Index: 6361781 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.5419. Min Act: -0.1700
Data Index: 8792665 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.5419. Min Act: -0.1700
Data Index: 2691938 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.4794. Min Act: -0.1700
Data Index: 2230310 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.4794. Min Act: -0.1700
Data Index: 8338233 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.4169. Min Act: -0.1700
Data Index: 8558828 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.4169. Min Act: -0.1700
Data Index: 4021993 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3856. Min Act: -0.1700
Data Index: 4795272 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3856. Min Act: -0.1700
Data Index: 2627821 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3544. Min Act: -0.1700
Data Index: 2718119 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3544. Min Act: -0.1700
Data Index: 6988068 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3544. Min Act: -0.1700
Data Index: 3928859 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3231. Min Act: -0.1700
Data Index: 3086385 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3231. Min Act: -0.1700
Data Index: 5072231 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3231. Min Act: -0.1700
Data Index: 5212015 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.3231. Min Act: -0.1700
Data Index: 8087332 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.2919. Min Act: -0.1700
Data Index: 69237 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.2919. Min Act: -0.1700
Data Index: 2585801 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7294. Min Range: -7.7294
Max Act: 7.2919. Min Act: -0.1700
Data Index: 1535875 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19