Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 147 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1853. Min Range: -9.1853
Max Act: 9.1853. Min Act: -0.1700
Data Index: 1343965 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1853. Min Range: -9.1853
Max Act: 9.1853. Min Act: -0.1700
Data Index: 4927522 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.8728. Min Act: -0.1700
Data Index: 5564648 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.8103. Min Act: -0.1700
Data Index: 7469330 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.8103. Min Act: -0.1700
Data Index: 5984708 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.8103. Min Act: -0.1700
Data Index: 5924285 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.7478. Min Act: -0.1700
Data Index: 2368535 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.7478. Min Act: -0.1700
Data Index: 2808750 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.7478. Min Act: -0.1700
Data Index: 5070387 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.7478. Min Act: -0.1700
Data Index: 6016744 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6228. Min Act: -0.1700
Data Index: 1954327 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6228. Min Act: -0.1700
Data Index: 4447422 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6228. Min Act: -0.1700
Data Index: 5745277 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6853. Min Act: -0.1700
Data Index: 820386 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6853. Min Act: -0.1700
Data Index: 2728827 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6228. Min Act: -0.1700
Data Index: 6282816 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.5603. Min Act: -0.1700
Data Index: 6317638 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6228. Min Act: -0.1700
Data Index: 4610747 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6228. Min Act: -0.1700
Data Index: 5924287 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1853. Min Range: -9.1853
Max Act: 8.6228. Min Act: -0.1700
Data Index: 2518061 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19