Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3017. Min Range: -7.3017
Max Act: 7.3017. Min Act: -0.1700
Data Index: 1041869 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3017. Min Range: -7.3017
Max Act: 7.1142. Min Act: -0.1700
Data Index: 3208994 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3017. Min Range: -7.3017
Max Act: 7.0205. Min Act: -0.1700
Data Index: 4032860 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3017. Min Range: -7.3017
Max Act: 7.0205. Min Act: -0.1700
Data Index: 6114220 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.9580. Min Act: -0.1700
Data Index: 802042 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.9267. Min Act: -0.1700
Data Index: 6448116 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.8955. Min Act: -0.1700
Data Index: 92708 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.8642. Min Act: -0.1697
Data Index: 4726253 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.8017. Min Act: -0.1700
Data Index: 893074 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.8017. Min Act: -0.1700
Data Index: 2729855 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.8017. Min Act: -0.1700
Data Index: 7112386 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.7705. Min Act: -0.1700
Data Index: 6448115 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.7392. Min Act: -0.1700
Data Index: 231743 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.7080. Min Act: -0.1700
Data Index: 6032420 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.6767. Min Act: -0.1700
Data Index: 7166319 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.6767. Min Act: -0.1700
Data Index: 5238515 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.6455. Min Act: -0.1700
Data Index: 7295742 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.6455. Min Act: -0.1700
Data Index: 5675794 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.6455. Min Act: -0.1700
Data Index: 6032423 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3017. Min Range: -7.3017
Max Act: 6.6142. Min Act: -0.1700
Data Index: 4117507 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19