Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2331 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1005. Min Range: -5.1005
Max Act: 5.1005. Min Act: -0.1700
Data Index: 1879867 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1005. Min Range: -5.1005
Max Act: 5.1005. Min Act: -0.1700
Data Index: 7795673 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1005. Min Range: -5.1005
Max Act: 5.0693. Min Act: -0.1700
Data Index: 8452473 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1005. Min Range: -5.1005
Max Act: 5.0380. Min Act: -0.1700
Data Index: 8452477 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1005. Min Range: -5.1005
Max Act: 5.0068. Min Act: -0.1700
Data Index: 343781 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1005. Min Range: -5.1005
Max Act: 5.0068. Min Act: -0.1700
Data Index: 3517460 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.9755. Min Act: -0.1700
Data Index: 188666 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.9755. Min Act: -0.1700
Data Index: 6509354 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.9130. Min Act: -0.1700
Data Index: 4849631 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.9443. Min Act: -0.1700
Data Index: 8500097 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.9443. Min Act: -0.1700
Data Index: 3517461 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8818. Min Act: -0.1700
Data Index: 1359301 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.9130. Min Act: -0.1700
Data Index: 8452279 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8818. Min Act: -0.1700
Data Index: 1719060 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8818. Min Act: -0.1700
Data Index: 1843886 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8505. Min Act: -0.1700
Data Index: 4849630 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8505. Min Act: -0.1700
Data Index: 2401979 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8505. Min Act: -0.1700
Data Index: 8452476 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8505. Min Act: -0.1700
Data Index: 861169 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1005. Min Range: -5.1005
Max Act: 4.8505. Min Act: -0.1700
Data Index: 4416554 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19