Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5772 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0997. Min Range: -7.0997
Max Act: 7.0997. Min Act: -0.1700
Data Index: 2014730 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0997. Min Range: -7.0997
Max Act: 7.0997. Min Act: -0.1700
Data Index: 343451 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0997. Min Range: -7.0997
Max Act: 7.0685. Min Act: -0.1700
Data Index: 6661611 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0997. Min Range: -7.0997
Max Act: 7.0685. Min Act: -0.1700
Data Index: 621905 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0997. Min Range: -7.0997
Max Act: 7.0372. Min Act: -0.1700
Data Index: 1160035 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0997. Min Range: -7.0997
Max Act: 7.0372. Min Act: -0.1700
Data Index: 8201359 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.9747. Min Act: -0.1700
Data Index: 8135041 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.9435. Min Act: -0.1700
Data Index: 7009317 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.9747. Min Act: -0.1700
Data Index: 7028658 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.9435. Min Act: -0.1700
Data Index: 1329670 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8810. Min Act: -0.1700
Data Index: 95478 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8810. Min Act: -0.1700
Data Index: 511740 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8497. Min Act: -0.1700
Data Index: 4606216 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8810. Min Act: -0.1700
Data Index: 7079022 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8185. Min Act: -0.1700
Data Index: 6476735 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8185. Min Act: -0.1700
Data Index: 5246826 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8185. Min Act: -0.1700
Data Index: 5766887 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.8497. Min Act: -0.1700
Data Index: 2423022 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.7872. Min Act: -0.1700
Data Index: 813587 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0997. Min Range: -7.0997
Max Act: 6.7872. Min Act: -0.1700
Data Index: 5673502 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19