Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4395 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.6468. Min Act: -0.1700
Data Index: 1619441 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.6468. Min Act: -0.1700
Data Index: 6627740 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.6155. Min Act: -0.1700
Data Index: 2215716 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.5843. Min Act: -0.1700
Data Index: 2846096 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.5530. Min Act: -0.1700
Data Index: 6627741 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.5530. Min Act: -0.1700
Data Index: 6627742 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.4905. Min Act: -0.1700
Data Index: 6831266 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.4593. Min Act: -0.1700
Data Index: 6913588 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.4280. Min Act: -0.1700
Data Index: 6664741 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.3968. Min Act: -0.1700
Data Index: 4076340 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.3343. Min Act: -0.1700
Data Index: 4565450 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.3968. Min Act: -0.1700
Data Index: 7693871 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.3343. Min Act: -0.1700
Data Index: 8507633 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.3030. Min Act: -0.1700
Data Index: 8253678 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.2718. Min Act: -0.1700
Data Index: 3784118 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.1780. Min Act: -0.1700
Data Index: 8260026 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.2093. Min Act: -0.1700
Data Index: 972343 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.2093. Min Act: -0.1700
Data Index: 2453567 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.1780. Min Act: -0.1700
Data Index: 3197310 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6468. Min Range: -6.6468
Max Act: 6.1780. Min Act: -0.1700
Data Index: 1668799 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19