Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2373 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.3505. Min Act: -0.1700
Data Index: 729808 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.1943. Min Act: -0.1700
Data Index: 676086 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.1318. Min Act: -0.1700
Data Index: 1598722 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.1318. Min Act: -0.1700
Data Index: 729810 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.0693. Min Act: -0.1700
Data Index: 1175365 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.0693. Min Act: -0.1700
Data Index: 3012134 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.0380. Min Act: -0.1700
Data Index: 2336683 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.0693. Min Act: -0.1700
Data Index: 2582078 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.0068. Min Act: -0.1700
Data Index: 7030740 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.0380. Min Act: -0.1700
Data Index: 6569710 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9443. Min Act: -0.1700
Data Index: 729809 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9755. Min Act: -0.1700
Data Index: 3904015 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3505. Min Range: -6.3505
Max Act: 6.0068. Min Act: -0.1700
Data Index: 130771 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9755. Min Act: -0.1700
Data Index: 4998897 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9755. Min Act: -0.1700
Data Index: 2008374 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9755. Min Act: -0.1700
Data Index: 4058042 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9755. Min Act: -0.1700
Data Index: 602705 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9130. Min Act: -0.1700
Data Index: 1414746 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9755. Min Act: -0.1700
Data Index: 3909859 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3505. Min Range: -6.3505
Max Act: 5.9443. Min Act: -0.1700
Data Index: 1549279 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19