Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.5016. Min Act: -0.1700
Data Index: 7627352 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.5016. Min Act: -0.1700
Data Index: 1744357 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.2828. Min Act: -0.1700
Data Index: 7080190 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.2203. Min Act: -0.1700
Data Index: 4358482 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.2516. Min Act: -0.1700
Data Index: 1508934 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.1578. Min Act: -0.1700
Data Index: 4499433 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.0641. Min Act: -0.1700
Data Index: 7733291 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5016. Min Range: -7.5016
Max Act: 7.0016. Min Act: -0.1700
Data Index: 1721676 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.9078. Min Act: -0.1700
Data Index: 5151316 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.8453. Min Act: -0.1700
Data Index: 8089967 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.7203. Min Act: -0.1700
Data Index: 4123909 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.7203. Min Act: -0.1700
Data Index: 8800769 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.6891. Min Act: -0.1700
Data Index: 8375426 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.6266. Min Act: -0.1700
Data Index: 291037 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.5953. Min Act: -0.1700
Data Index: 4914280 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.5953. Min Act: -0.1700
Data Index: 7816867 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.5641. Min Act: -0.1700
Data Index: 725546 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.5641. Min Act: -0.1700
Data Index: 2557630 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.5641. Min Act: -0.1700
Data Index: 6629979 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5016. Min Range: -7.5016
Max Act: 6.5953. Min Act: -0.1700
Data Index: 1527977 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19