Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.2125. Min Act: -0.1700
Data Index: 1826319 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.1812. Min Act: -0.1700
Data Index: 6374469 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.1812. Min Act: -0.1700
Data Index: 3190879 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.1187. Min Act: -0.1700
Data Index: 1709944 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.1187. Min Act: -0.1700
Data Index: 6586498 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.0562. Min Act: -0.1700
Data Index: 3502647 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.0562. Min Act: -0.1700
Data Index: 4446770 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.0562. Min Act: -0.1700
Data Index: 5410871 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.0562. Min Act: -0.1700
Data Index: 14897 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.0250. Min Act: -0.1700
Data Index: 4712766 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.0250. Min Act: -0.1700
Data Index: 7879182 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2125. Min Range: -6.2125
Max Act: 6.0250. Min Act: -0.1700
Data Index: 3128248 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9937. Min Act: -0.1700
Data Index: 3818357 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9937. Min Act: -0.1700
Data Index: 6930280 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9937. Min Act: -0.1700
Data Index: 6750812 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9937. Min Act: -0.1700
Data Index: 2431894 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9937. Min Act: -0.1700
Data Index: 659656 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9937. Min Act: -0.1700
Data Index: 5723609 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9625. Min Act: -0.1700
Data Index: 4934358 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2125. Min Range: -6.2125
Max Act: 5.9625. Min Act: -0.1700
Data Index: 2268376 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19