Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2294. Min Range: -8.2294
Max Act: 8.2294. Min Act: -0.1700
Data Index: 8466496 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2294. Min Range: -8.2294
Max Act: 8.2294. Min Act: -0.1700
Data Index: 1443704 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2294. Min Range: -8.2294
Max Act: 8.1669. Min Act: -0.1700
Data Index: 5258445 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2294. Min Range: -8.2294
Max Act: 8.1669. Min Act: -0.1700
Data Index: 1007378 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.9794. Min Act: -0.1700
Data Index: 2923542 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.9169. Min Act: -0.1700
Data Index: 1246400 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.9169. Min Act: -0.1700
Data Index: 3441307 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7919. Min Act: -0.1700
Data Index: 7648541 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7607. Min Act: -0.1700
Data Index: 1194250 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7607. Min Act: -0.1700
Data Index: 1634085 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7294. Min Act: -0.1700
Data Index: 5620073 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7294. Min Act: -0.1700
Data Index: 2331204 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7294. Min Act: -0.1700
Data Index: 4164079 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7294. Min Act: -0.1700
Data Index: 3127878 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.7294. Min Act: -0.1700
Data Index: 6020265 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.6669. Min Act: -0.1700
Data Index: 4402902 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.6982. Min Act: -0.1700
Data Index: 7703682 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.6982. Min Act: -0.1700
Data Index: 3709966 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.6982. Min Act: -0.1700
Data Index: 1781189 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2294. Min Range: -8.2294
Max Act: 7.6982. Min Act: -0.1700
Data Index: 4744458 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19