Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4991 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.3555. Min Act: -0.1700
Data Index: 5883985 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.3243. Min Act: -0.1700
Data Index: 1688495 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.2930. Min Act: -0.1700
Data Index: 8664981 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.2618. Min Act: -0.1700
Data Index: 6466676 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.2305. Min Act: -0.1700
Data Index: 7558293 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1993. Min Act: -0.1700
Data Index: 340454 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1993. Min Act: -0.1700
Data Index: 1603452 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1993. Min Act: -0.1700
Data Index: 4961585 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1993. Min Act: -0.1700
Data Index: 6100374 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1680. Min Act: -0.1700
Data Index: 798633 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1680. Min Act: -0.1700
Data Index: 1549830 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1680. Min Act: -0.1700
Data Index: 6841120 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1680. Min Act: -0.1700
Data Index: 440337 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1680. Min Act: -0.1700
Data Index: 1086418 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1367. Min Act: -0.1700
Data Index: 2826413 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1055. Min Act: -0.1700
Data Index: 7866576 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.1055. Min Act: -0.1700
Data Index: 1737231 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.0430. Min Act: -0.1700
Data Index: 5093304 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.0742. Min Act: -0.1700
Data Index: 6350533 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3555. Min Range: -4.3555
Max Act: 4.0742. Min Act: -0.1700
Data Index: 4009530 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19