Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.5298. Min Act: -0.1700
Data Index: 5283125 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.4986. Min Act: -0.1700
Data Index: 6758220 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.3111. Min Act: -0.1700
Data Index: 147148 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.1548. Min Act: -0.1700
Data Index: 294732 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.1236. Min Act: -0.1700
Data Index: 7857628 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.0611. Min Act: -0.1700
Data Index: 256948 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.0298. Min Act: -0.1700
Data Index: 3860225 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.0298. Min Act: -0.1700
Data Index: 7750146 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5298. Min Range: -7.5298
Max Act: 7.0298. Min Act: -0.1700
Data Index: 1686868 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.9673. Min Act: -0.1700
Data Index: 1739593 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.9673. Min Act: -0.1700
Data Index: 2977674 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.9048. Min Act: -0.1700
Data Index: 4575854 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.9361. Min Act: -0.1700
Data Index: 605175 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.9048. Min Act: -0.1700
Data Index: 5487316 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.9361. Min Act: -0.1700
Data Index: 6038855 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.9048. Min Act: -0.1700
Data Index: 250923 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.8736. Min Act: -0.1700
Data Index: 8006448 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.8111. Min Act: -0.1700
Data Index: 4983025 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.8111. Min Act: -0.1700
Data Index: 1615922 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5298. Min Range: -7.5298
Max Act: 6.8111. Min Act: -0.1700
Data Index: 7750145 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19