Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.4535. Min Act: -0.1700
Data Index: 1029449 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.3910. Min Act: -0.1700
Data Index: 5117587 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.4223. Min Act: -0.1700
Data Index: 2548047 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.3910. Min Act: -0.1700
Data Index: 1409977 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.3598. Min Act: -0.1700
Data Index: 4386899 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.3598. Min Act: -0.1700
Data Index: 5895944 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.3285. Min Act: -0.1700
Data Index: 4987891 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.3285. Min Act: -0.1699
Data Index: 5922822 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.2973. Min Act: -0.1700
Data Index: 4002171 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.2348. Min Act: -0.1700
Data Index: 5958103 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.2035. Min Act: -0.1700
Data Index: 7819023 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.2035. Min Act: -0.1700
Data Index: 5576142 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.1723. Min Act: -0.1700
Data Index: 3817592 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.1410. Min Act: -0.1700
Data Index: 5471637 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.1410. Min Act: -0.1700
Data Index: 1221074 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.1410. Min Act: -0.1700
Data Index: 5194365 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.1410. Min Act: -0.1700
Data Index: 4365921 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.1410. Min Act: -0.1700
Data Index: 6466670 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.0785. Min Act: -0.1700
Data Index: 3502121 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4535. Min Range: -6.4535
Max Act: 6.1098. Min Act: -0.1700
Data Index: 7548651 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19