Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.4392. Min Act: -0.1700
Data Index: 3636871 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.3767. Min Act: -0.1700
Data Index: 6956254 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.3454. Min Act: -0.1700
Data Index: 6150356 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.3142. Min Act: -0.1700
Data Index: 1609317 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.2517. Min Act: -0.1700
Data Index: 2853530 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.2204. Min Act: -0.1700
Data Index: 458648 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.1579. Min Act: -0.1700
Data Index: 4958841 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.1267. Min Act: -0.1700
Data Index: 3662127 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.0642. Min Act: -0.1700
Data Index: 8396657 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.0329. Min Act: -0.1700
Data Index: 5197332 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.0329. Min Act: -0.1700
Data Index: 8744200 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.0329. Min Act: -0.1700
Data Index: 6174450 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.0642. Min Act: -0.1700
Data Index: 7860402 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.0329. Min Act: -0.1700
Data Index: 750064 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4392. Min Range: -6.4392
Max Act: 6.0329. Min Act: -0.1700
Data Index: 7393685 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4392. Min Range: -6.4392
Max Act: 5.9704. Min Act: -0.1700
Data Index: 1837650 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4392. Min Range: -6.4392
Max Act: 5.9704. Min Act: -0.1700
Data Index: 8051717 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4392. Min Range: -6.4392
Max Act: 5.9392. Min Act: -0.1700
Data Index: 4186209 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4392. Min Range: -6.4392
Max Act: 5.9392. Min Act: -0.1700
Data Index: 5018746 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4392. Min Range: -6.4392
Max Act: 5.9392. Min Act: -0.1700
Data Index: 405639 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19