Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2791 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.9239. Min Act: -0.1700
Data Index: 4322222 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.8302. Min Act: -0.1700
Data Index: 7389666 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.6114. Min Act: -0.1700
Data Index: 5392620 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.6114. Min Act: -0.1700
Data Index: 5290699 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.5177. Min Act: -0.1700
Data Index: 1525613 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.4552. Min Act: -0.1700
Data Index: 4144919 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.4552. Min Act: -0.1700
Data Index: 3051463 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.4864. Min Act: -0.1700
Data Index: 7631038 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.4239. Min Act: -0.1700
Data Index: 8445426 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.4239. Min Act: -0.1700
Data Index: 8532731 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.4239. Min Act: -0.1700
Data Index: 107034 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3927. Min Act: -0.1700
Data Index: 433291 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3927. Min Act: -0.1700
Data Index: 133766 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3927. Min Act: -0.1700
Data Index: 8214048 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3927. Min Act: -0.1700
Data Index: 6818457 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3614. Min Act: -0.1700
Data Index: 2017742 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3614. Min Act: -0.1700
Data Index: 443312 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3302. Min Act: -0.1700
Data Index: 7771456 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.2989. Min Act: -0.1700
Data Index: 7962515 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9239. Min Range: -6.9239
Max Act: 6.3302. Min Act: -0.1700
Data Index: 680419 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19