Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.7010. Min Act: -0.1700
Data Index: 4384127 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.6385. Min Act: -0.1700
Data Index: 7274310 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.5448. Min Act: -0.1700
Data Index: 6078040 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.4510. Min Act: -0.1700
Data Index: 3337850 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.4198. Min Act: -0.1700
Data Index: 1060393 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.2635. Min Act: -0.1700
Data Index: 412437 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.2323. Min Act: -0.1700
Data Index: 5116579 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.2323. Min Act: -0.1700
Data Index: 3084345 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.2010. Min Act: -0.1700
Data Index: 8214619 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1698. Min Act: -0.1700
Data Index: 863451 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1698. Min Act: -0.1700
Data Index: 4778780 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1385. Min Act: -0.1700
Data Index: 3518274 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1385. Min Act: -0.1700
Data Index: 2939089 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1385. Min Act: -0.1700
Data Index: 7795725 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1385. Min Act: -0.1700
Data Index: 2039945 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1073. Min Act: -0.1700
Data Index: 7984219 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.1073. Min Act: -0.1700
Data Index: 1973874 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.0760. Min Act: -0.1700
Data Index: 8772627 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.0760. Min Act: -0.1700
Data Index: 5597860 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7010. Min Range: -6.7010
Max Act: 6.0448. Min Act: -0.1700
Data Index: 3762300 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19