Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4550 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.6828. Min Act: -0.1700
Data Index: 366340 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.5578. Min Act: -0.1700
Data Index: 6376116 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.5578. Min Act: -0.1700
Data Index: 7890538 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.5578. Min Act: -0.1700
Data Index: 4164351 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.4953. Min Act: -0.1700
Data Index: 7425650 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.4328. Min Act: -0.1700
Data Index: 7347231 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.4328. Min Act: -0.1700
Data Index: 2438259 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.4328. Min Act: -0.1700
Data Index: 1261389 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.3703. Min Act: -0.1700
Data Index: 7152231 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.3078. Min Act: -0.1700
Data Index: 5225459 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.3078. Min Act: -0.1700
Data Index: 2915488 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.3078. Min Act: -0.1700
Data Index: 7793540 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.2453. Min Act: -0.1700
Data Index: 2496622 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.2453. Min Act: -0.1700
Data Index: 4844165 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.1828. Min Act: -0.1700
Data Index: 1763276 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.1828. Min Act: -0.1700
Data Index: 8437039 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.0578. Min Act: -0.1700
Data Index: 6692579 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.1203. Min Act: -0.1700
Data Index: 3799967 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.0578. Min Act: -0.1700
Data Index: 1746255 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6828. Min Range: -9.6828
Max Act: 9.0578. Min Act: -0.1700
Data Index: 4887123 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19