Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3156 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2171. Min Range: -7.2171
Max Act: 7.2171. Min Act: -0.1700
Data Index: 3963210 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2171. Min Range: -7.2171
Max Act: 7.1858. Min Act: -0.1700
Data Index: 8336561 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2171. Min Range: -7.2171
Max Act: 7.0608. Min Act: -0.1700
Data Index: 8770217 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.9046. Min Act: -0.1700
Data Index: 6189149 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.9046. Min Act: -0.1700
Data Index: 3294172 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.9046. Min Act: -0.1700
Data Index: 5857950 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.9046. Min Act: -0.1700
Data Index: 5636511 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.8421. Min Act: -0.1700
Data Index: 4462087 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.8421. Min Act: -0.1700
Data Index: 1342527 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.7796. Min Act: -0.1700
Data Index: 1839903 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.7483. Min Act: -0.1700
Data Index: 6529171 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.7171. Min Act: -0.1700
Data Index: 7113411 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.7171. Min Act: -0.1700
Data Index: 4796362 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.6858. Min Act: -0.1700
Data Index: 6008772 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.6546. Min Act: -0.1700
Data Index: 7701743 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.6233. Min Act: -0.1700
Data Index: 1264811 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.5921. Min Act: -0.1700
Data Index: 4176577 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.5921. Min Act: -0.1700
Data Index: 3052001 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.5608. Min Act: -0.1700
Data Index: 6393713 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2171. Min Range: -7.2171
Max Act: 6.5921. Min Act: -0.1700
Data Index: 3647329 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19