Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4459 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.7511. Min Act: -0.1700
Data Index: 6281265 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.6261. Min Act: -0.1700
Data Index: 5890944 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.5011. Min Act: -0.1700
Data Index: 2582918 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.4699. Min Act: -0.1700
Data Index: 6929409 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.4074. Min Act: -0.1700
Data Index: 7799989 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.3449. Min Act: -0.1700
Data Index: 907800 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.3449. Min Act: -0.1700
Data Index: 7594881 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.2824. Min Act: -0.1700
Data Index: 1294863 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.2511. Min Act: -0.1700
Data Index: 4124768 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.2199. Min Act: -0.1700
Data Index: 3568031 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.2199. Min Act: -0.1700
Data Index: 5297077 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.2199. Min Act: -0.1700
Data Index: 790744 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1886. Min Act: -0.1700
Data Index: 7939757 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1886. Min Act: -0.1700
Data Index: 859832 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1574. Min Act: -0.1700
Data Index: 681158 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1574. Min Act: -0.1700
Data Index: 7811475 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1574. Min Act: -0.1700
Data Index: 2114630 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1574. Min Act: -0.1700
Data Index: 7245158 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1261. Min Act: -0.1700
Data Index: 2374644 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7511. Min Range: -6.7511
Max Act: 6.1261. Min Act: -0.1700
Data Index: 2391948 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19