Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2094. Min Range: -5.2094
Max Act: 5.2094. Min Act: -0.1700
Data Index: 7609013 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2094. Min Range: -5.2094
Max Act: 5.1782. Min Act: -0.1700
Data Index: 490143 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2094. Min Range: -5.2094
Max Act: 5.1782. Min Act: -0.1700
Data Index: 984546 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2094. Min Range: -5.2094
Max Act: 5.1782. Min Act: -0.1700
Data Index: 3958322 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2094. Min Range: -5.2094
Max Act: 5.1157. Min Act: -0.1700
Data Index: 7697637 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2094. Min Range: -5.2094
Max Act: 5.0844. Min Act: -0.1700
Data Index: 3958321 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2094. Min Range: -5.2094
Max Act: 5.0532. Min Act: -0.1700
Data Index: 2481863 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.9907. Min Act: -0.1700
Data Index: 807704 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.9907. Min Act: -0.1700
Data Index: 634654 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.9594. Min Act: -0.1700
Data Index: 4829040 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.9282. Min Act: -0.1700
Data Index: 4082522 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.9282. Min Act: -0.1700
Data Index: 8175791 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.8969. Min Act: -0.1700
Data Index: 4164903 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.8344. Min Act: -0.1700
Data Index: 4786229 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.8344. Min Act: -0.1700
Data Index: 5406335 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.8032. Min Act: -0.1700
Data Index: 4512735 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.7719. Min Act: -0.1700
Data Index: 7132402 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.7407. Min Act: -0.1700
Data Index: 4904136 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.7094. Min Act: -0.1700
Data Index: 7070174 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2094. Min Range: -5.2094
Max Act: 4.6782. Min Act: -0.1700
Data Index: 8285468 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19