Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.8725. Min Act: -0.1700
Data Index: 4060336 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.8100. Min Act: -0.1700
Data Index: 8391908 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.7162. Min Act: -0.1700
Data Index: 348912 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6850. Min Act: -0.1700
Data Index: 3996331 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6850. Min Act: -0.1700
Data Index: 2428351 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6537. Min Act: -0.1700
Data Index: 5141252 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6537. Min Act: -0.1700
Data Index: 4212620 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6225. Min Act: -0.1700
Data Index: 6253449 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6225. Min Act: -0.1700
Data Index: 472173 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6225. Min Act: -0.1700
Data Index: 321943 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.6225. Min Act: -0.1700
Data Index: 7537160 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5912. Min Act: -0.1700
Data Index: 4491974 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5600. Min Act: -0.1700
Data Index: 5220061 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5912. Min Act: -0.1700
Data Index: 6167462 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5912. Min Act: -0.1700
Data Index: 4065061 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5600. Min Act: -0.1700
Data Index: 5429230 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5600. Min Act: -0.1700
Data Index: 1840043 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5600. Min Act: -0.1700
Data Index: 4210725 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5600. Min Act: -0.1700
Data Index: 5609965 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8725. Min Range: -4.8725
Max Act: 4.5600. Min Act: -0.1700
Data Index: 2418270 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19