Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.3579. Min Act: -0.1700
Data Index: 5382904 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.3266. Min Act: -0.1700
Data Index: 1511155 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.2641. Min Act: -0.1700
Data Index: 1831870 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.2329. Min Act: -0.1700
Data Index: 5929223 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.2016. Min Act: -0.1700
Data Index: 8403341 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 4631638 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 2275427 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 129247 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 2978792 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.2016. Min Act: -0.1700
Data Index: 16825 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 2821810 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 3742805 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 2079086 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1391. Min Act: -0.1700
Data Index: 7904117 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1704. Min Act: -0.1700
Data Index: 8793512 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1079. Min Act: -0.1700
Data Index: 5575141 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1079. Min Act: -0.1700
Data Index: 5263806 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.0766. Min Act: -0.1700
Data Index: 8527960 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1079. Min Act: -0.1700
Data Index: 7140921 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3579. Min Range: -7.3579
Max Act: 7.1079. Min Act: -0.1700
Data Index: 252561 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19