Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.8410. Min Act: -0.1700
Data Index: 7069173 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.8410. Min Act: -0.1700
Data Index: 8097482 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7628. Min Act: -0.1700
Data Index: 7256305 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7472. Min Act: -0.1700
Data Index: 4224718 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7315. Min Act: -0.1700
Data Index: 4433413 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7472. Min Act: -0.1700
Data Index: 7750118 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7315. Min Act: -0.1700
Data Index: 1450908 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7159. Min Act: -0.1700
Data Index: 3537471 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7315. Min Act: -0.1700
Data Index: 360901 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7315. Min Act: -0.1700
Data Index: 4163589 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7159. Min Act: -0.1700
Data Index: 3700649 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.7003. Min Act: -0.1700
Data Index: 5414424 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6846. Min Act: -0.1700
Data Index: 2835930 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6846. Min Act: -0.1700
Data Index: 1784393 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6846. Min Act: -0.1700
Data Index: 1332586 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6690. Min Act: -0.1700
Data Index: 935881 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6690. Min Act: -0.1700
Data Index: 6344213 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6846. Min Act: -0.1700
Data Index: 7020850 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6533. Min Act: -0.1700
Data Index: 2253918 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8410. Min Range: -3.8410
Max Act: 3.6533. Min Act: -0.1700
Data Index: 4759497 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19