Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1114. Min Range: -6.1114
Max Act: 6.1114. Min Act: -0.1700
Data Index: 6422258 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1114. Min Range: -6.1114
Max Act: 6.1114. Min Act: -0.1700
Data Index: 967339 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1114. Min Range: -6.1114
Max Act: 6.0177. Min Act: -0.1700
Data Index: 8262232 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9864. Min Act: -0.1700
Data Index: 4160166 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9864. Min Act: -0.1700
Data Index: 6107655 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9552. Min Act: -0.1700
Data Index: 2989552 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9552. Min Act: -0.1700
Data Index: 2989570 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8927. Min Act: -0.1700
Data Index: 3822390 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9239. Min Act: -0.1700
Data Index: 5885893 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9552. Min Act: -0.1700
Data Index: 2989555 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9239. Min Act: -0.1700
Data Index: 8278936 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9239. Min Act: -0.1700
Data Index: 4662390 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.9239. Min Act: -0.1700
Data Index: 6155208 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8927. Min Act: -0.1700
Data Index: 7379790 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8614. Min Act: -0.1700
Data Index: 2989563 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8614. Min Act: -0.1700
Data Index: 580750 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8614. Min Act: -0.1700
Data Index: 2989577 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8614. Min Act: -0.1700
Data Index: 6296659 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8614. Min Act: -0.1700
Data Index: 1251915 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1114. Min Range: -6.1114
Max Act: 5.8614. Min Act: -0.1700
Data Index: 4662391 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19