Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3345. Min Range: -6.3345
Max Act: 6.3345. Min Act: -0.1700
Data Index: 5295558 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3345. Min Range: -6.3345
Max Act: 6.0845. Min Act: -0.1700
Data Index: 334273 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3345. Min Range: -6.3345
Max Act: 6.0532. Min Act: -0.1700
Data Index: 1060908 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3345. Min Range: -6.3345
Max Act: 6.0532. Min Act: -0.1700
Data Index: 6997821 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3345. Min Range: -6.3345
Max Act: 6.0220. Min Act: -0.1700
Data Index: 6074077 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.9595. Min Act: -0.1700
Data Index: 2540915 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.9595. Min Act: -0.1700
Data Index: 4701356 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.9282. Min Act: -0.1700
Data Index: 2304054 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8970. Min Act: -0.1700
Data Index: 554790 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8970. Min Act: -0.1700
Data Index: 1708268 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8970. Min Act: -0.1700
Data Index: 1500119 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8657. Min Act: -0.1700
Data Index: 3866427 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8657. Min Act: -0.1700
Data Index: 2073442 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8657. Min Act: -0.1700
Data Index: 7038121 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8345. Min Act: -0.1700
Data Index: 6157843 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8345. Min Act: -0.1700
Data Index: 1708267 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8657. Min Act: -0.1700
Data Index: 2387233 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8032. Min Act: -0.1700
Data Index: 5016926 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8032. Min Act: -0.1700
Data Index: 7448851 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3345. Min Range: -6.3345
Max Act: 5.8032. Min Act: -0.1700
Data Index: 5735784 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19