Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1014 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.4798. Min Act: -0.1700
Data Index: 3121955 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.4486. Min Act: -0.1700
Data Index: 6464634 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.4173. Min Act: -0.1700
Data Index: 8556078 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.3548. Min Act: -0.1700
Data Index: 6936492 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.3236. Min Act: -0.1700
Data Index: 1386488 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.3236. Min Act: -0.1700
Data Index: 4451646 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.3236. Min Act: -0.1700
Data Index: 3768458 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.2611. Min Act: -0.1700
Data Index: 4435809 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.2611. Min Act: -0.1700
Data Index: 6546711 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.2611. Min Act: -0.1700
Data Index: 3720667 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.1673. Min Act: -0.1700
Data Index: 7614614 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.1673. Min Act: -0.1700
Data Index: 5182967 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.1360. Min Act: -0.1700
Data Index: 1483627 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.1360. Min Act: -0.1700
Data Index: 318901 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.1360. Min Act: -0.1700
Data Index: 3770651 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.1048. Min Act: -0.1700
Data Index: 302159 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.0735. Min Act: -0.1700
Data Index: 2422803 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.0735. Min Act: -0.1700
Data Index: 4263787 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.1048. Min Act: -0.1700
Data Index: 1983009 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4798. Min Range: -4.4798
Max Act: 4.0735. Min Act: -0.1700
Data Index: 5344530 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19