Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4871 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1856. Min Range: -5.1856
Max Act: 5.1856. Min Act: -0.1700
Data Index: 3036002 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1856. Min Range: -5.1856
Max Act: 5.1231. Min Act: -0.1700
Data Index: 3036001 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1856. Min Range: -5.1856
Max Act: 5.0918. Min Act: -0.1700
Data Index: 4876507 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1856. Min Range: -5.1856
Max Act: 5.0293. Min Act: -0.1700
Data Index: 205675 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1856. Min Range: -5.1856
Max Act: 5.0293. Min Act: -0.1700
Data Index: 6157912 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1856. Min Range: -5.1856
Max Act: 5.0293. Min Act: -0.1700
Data Index: 534555 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2205043 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.9981. Min Act: -0.1700
Data Index: 885878 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.9668. Min Act: -0.1700
Data Index: 5878535 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.9668. Min Act: -0.1700
Data Index: 3565345 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.9668. Min Act: -0.1700
Data Index: 8021758 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.9356. Min Act: -0.1700
Data Index: 3433374 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.9356. Min Act: -0.1700
Data Index: 7986693 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.8731. Min Act: -0.1700
Data Index: 534566 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.8731. Min Act: -0.1700
Data Index: 3970546 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.8418. Min Act: -0.1700
Data Index: 3463593 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.8106. Min Act: -0.1700
Data Index: 5806219 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.7793. Min Act: -0.1700
Data Index: 494092 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.7481. Min Act: -0.1700
Data Index: 7019509 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1856. Min Range: -5.1856
Max Act: 4.7481. Min Act: -0.1700
Data Index: 5896831 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19