Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1042 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3113. Min Range: -6.3113
Max Act: 6.3113. Min Act: -0.1700
Data Index: 8154230 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9675. Min Act: -0.1700
Data Index: 8487899 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9675. Min Act: -0.1700
Data Index: 5149543 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9675. Min Act: -0.1700
Data Index: 129655 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9675. Min Act: -0.1700
Data Index: 2294743 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9363. Min Act: -0.1700
Data Index: 6776911 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9363. Min Act: -0.1700
Data Index: 2640695 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8738. Min Act: -0.1700
Data Index: 2422611 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9050. Min Act: -0.1700
Data Index: 6672320 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9050. Min Act: -0.1700
Data Index: 4219361 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8738. Min Act: -0.1700
Data Index: 7138803 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8425. Min Act: -0.1700
Data Index: 2354813 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8425. Min Act: -0.1700
Data Index: 1615420 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8425. Min Act: -0.1700
Data Index: 7887157 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8425. Min Act: -0.1700
Data Index: 7917426 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8425. Min Act: -0.1700
Data Index: 7236039 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 483463 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 128788 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.7800. Min Act: -0.1700
Data Index: 6249960 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.7800. Min Act: -0.1700
Data Index: 5039137 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19