Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 82 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.5682. Min Act: -0.1700
Data Index: 1162114 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.4745. Min Act: -0.1700
Data Index: 1729795 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.3182. Min Act: -0.1700
Data Index: 4148513 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.1932. Min Act: -0.1700
Data Index: 892698 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.1307. Min Act: -0.1700
Data Index: 3899937 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.1307. Min Act: -0.1700
Data Index: 6120890 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.1307. Min Act: -0.1700
Data Index: 1349706 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0995. Min Act: -0.1700
Data Index: 8825576 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0682. Min Act: -0.1700
Data Index: 1728542 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0995. Min Act: -0.1700
Data Index: 2681056 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0370. Min Act: -0.1700
Data Index: 6380210 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0370. Min Act: -0.1700
Data Index: 7788059 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0370. Min Act: -0.1700
Data Index: 5557386 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0370. Min Act: -0.1700
Data Index: 5923249 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0057. Min Act: -0.1700
Data Index: 2065623 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0057. Min Act: -0.1700
Data Index: 7904546 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0057. Min Act: -0.1700
Data Index: 8075383 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0057. Min Act: -0.1700
Data Index: 8060421 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0057. Min Act: -0.1700
Data Index: 1298168 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5682. Min Range: -5.5682
Max Act: 5.0057. Min Act: -0.1700
Data Index: 7949686 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19