Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.9679. Min Act: -0.1700
Data Index: 5366085 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.6866. Min Act: -0.1700
Data Index: 1720260 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.6866. Min Act: -0.1700
Data Index: 3834344 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.6866. Min Act: -0.1700
Data Index: 3135419 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.6866. Min Act: -0.1700
Data Index: 6787383 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.5929. Min Act: -0.1700
Data Index: 2718287 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.5616. Min Act: -0.1700
Data Index: 2008209 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.5304. Min Act: -0.1700
Data Index: 4949830 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4991. Min Act: -0.1700
Data Index: 8682588 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.5616. Min Act: -0.1700
Data Index: 2944307 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.5304. Min Act: -0.1700
Data Index: 7505109 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4991. Min Act: -0.1700
Data Index: 6302508 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4991. Min Act: -0.1700
Data Index: 1607382 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4991. Min Act: -0.1700
Data Index: 8324739 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4991. Min Act: -0.1700
Data Index: 4918328 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4991. Min Act: -0.1700
Data Index: 7326081 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4679. Min Act: -0.1700
Data Index: 3752352 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4679. Min Act: -0.1700
Data Index: 4808196 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4679. Min Act: -0.1700
Data Index: 5867185 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9679. Min Range: -4.9679
Max Act: 4.4679. Min Act: -0.1700
Data Index: 5301396 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19