Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.6842. Min Act: -0.1700
Data Index: 1522904 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.5592. Min Act: -0.1700
Data Index: 8161465 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.5279. Min Act: -0.1700
Data Index: 6125432 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.5279. Min Act: -0.1700
Data Index: 4217541 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4654. Min Act: -0.1700
Data Index: 6969398 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4967. Min Act: -0.1700
Data Index: 3827461 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4654. Min Act: -0.1700
Data Index: 850952 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4342. Min Act: -0.1700
Data Index: 5900190 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4654. Min Act: -0.1699
Data Index: 3850059 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4654. Min Act: -0.1700
Data Index: 596789 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4342. Min Act: -0.1700
Data Index: 207797 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4654. Min Act: -0.1700
Data Index: 1867658 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4029. Min Act: -0.1700
Data Index: 4624025 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4342. Min Act: -0.1700
Data Index: 7675128 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4342. Min Act: -0.1700
Data Index: 6944783 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4342. Min Act: -0.1700
Data Index: 7025367 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4029. Min Act: -0.1700
Data Index: 3363134 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4029. Min Act: -0.1700
Data Index: 3501943 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4029. Min Act: -0.1700
Data Index: 6769154 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6842. Min Range: -4.6842
Max Act: 4.4029. Min Act: -0.1700
Data Index: 6803670 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19