Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2060. Min Range: -8.2060
Max Act: 8.2060. Min Act: -0.1700
Data Index: 7453413 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2060. Min Range: -8.2060
Max Act: 8.1435. Min Act: -0.1700
Data Index: 7453411 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2060. Min Range: -8.2060
Max Act: 8.1122. Min Act: -0.1700
Data Index: 8356115 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.9872. Min Act: -0.1700
Data Index: 5355919 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.9247. Min Act: -0.1700
Data Index: 397400 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.9247. Min Act: -0.1700
Data Index: 7453412 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.9247. Min Act: -0.1700
Data Index: 4442123 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.8935. Min Act: -0.1700
Data Index: 1120366 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.8935. Min Act: -0.1700
Data Index: 7453409 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.8622. Min Act: -0.1700
Data Index: 999591 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.6747. Min Act: -0.1700
Data Index: 5124709 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.7060. Min Act: -0.1700
Data Index: 1344076 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.6435. Min Act: -0.1700
Data Index: 8622782 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.6122. Min Act: -0.1700
Data Index: 7692448 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.6122. Min Act: -0.1700
Data Index: 7519709 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.5810. Min Act: -0.1700
Data Index: 2685635 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.5810. Min Act: -0.1700
Data Index: 1803947 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.5497. Min Act: -0.1700
Data Index: 4432674 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.5497. Min Act: -0.1700
Data Index: 1833506 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2060. Min Range: -8.2060
Max Act: 7.5185. Min Act: -0.1700
Data Index: 7951603 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19