Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1128. Min Range: -5.1128
Max Act: 5.1128. Min Act: -0.1700
Data Index: 1993841 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1128. Min Range: -5.1128
Max Act: 5.1128. Min Act: -0.1700
Data Index: 7951558 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.8940. Min Act: -0.1700
Data Index: 2680921 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.8628. Min Act: -0.1700
Data Index: 7065551 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.8315. Min Act: -0.1700
Data Index: 5991544 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.8003. Min Act: -0.1700
Data Index: 2462216 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.8003. Min Act: -0.1700
Data Index: 2680925 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.8003. Min Act: -0.1700
Data Index: 8312405 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.7690. Min Act: -0.1700
Data Index: 2462222 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.7378. Min Act: -0.1700
Data Index: 6916980 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.7378. Min Act: -0.1700
Data Index: 8128934 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.7378. Min Act: -0.1700
Data Index: 1597391 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.6753. Min Act: -0.1700
Data Index: 8345858 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.6753. Min Act: -0.1700
Data Index: 1676704 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.7065. Min Act: -0.1700
Data Index: 8128920 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.6753. Min Act: -0.1700
Data Index: 6539248 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.6753. Min Act: -0.1700
Data Index: 1597376 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.6440. Min Act: -0.1700
Data Index: 2746206 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.6440. Min Act: -0.1700
Data Index: 5863470 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1128. Min Range: -5.1128
Max Act: 4.6128. Min Act: -0.1700
Data Index: 1867580 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19