Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1944. Min Range: -7.1944
Max Act: 7.1944. Min Act: -0.1700
Data Index: 2000866 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1944. Min Range: -7.1944
Max Act: 7.1007. Min Act: -0.1700
Data Index: 4222222 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1944. Min Range: -7.1944
Max Act: 7.1007. Min Act: -0.1700
Data Index: 2640950 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1944. Min Range: -7.1944
Max Act: 7.0382. Min Act: -0.1700
Data Index: 3838833 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1944. Min Range: -7.1944
Max Act: 7.0382. Min Act: -0.1700
Data Index: 6142280 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.9757. Min Act: -0.1700
Data Index: 7469109 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.8819. Min Act: -0.1700
Data Index: 4899989 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.8819. Min Act: -0.1700
Data Index: 92999 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.8819. Min Act: -0.1700
Data Index: 4715152 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.8194. Min Act: -0.1700
Data Index: 4899990 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.7882. Min Act: -0.1700
Data Index: 4222221 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.7882. Min Act: -0.1700
Data Index: 93000 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.7569. Min Act: -0.1700
Data Index: 2693213 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.7257. Min Act: -0.1700
Data Index: 5002280 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.7569. Min Act: -0.1700
Data Index: 3150160 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.7569. Min Act: -0.1700
Data Index: 3866813 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.7257. Min Act: -0.1700
Data Index: 8294277 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.6944. Min Act: -0.1700
Data Index: 4715153 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.6944. Min Act: -0.1700
Data Index: 7400751 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1944. Min Range: -7.1944
Max Act: 6.6944. Min Act: -0.1700
Data Index: 4262960 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19