Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1412. Min Range: -6.1412
Max Act: 6.1412. Min Act: -0.1700
Data Index: 4568171 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.9849. Min Act: -0.1700
Data Index: 841457 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.9224. Min Act: -0.1700
Data Index: 3929083 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.9224. Min Act: -0.1700
Data Index: 6929175 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.8599. Min Act: -0.1700
Data Index: 4186211 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.8912. Min Act: -0.1700
Data Index: 6975250 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.8599. Min Act: -0.1700
Data Index: 2150339 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.8287. Min Act: -0.1700
Data Index: 2546837 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7974. Min Act: -0.1700
Data Index: 3743933 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7974. Min Act: -0.1700
Data Index: 7173397 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7974. Min Act: -0.1700
Data Index: 7174116 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7974. Min Act: -0.1700
Data Index: 268952 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7662. Min Act: -0.1700
Data Index: 7324384 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7662. Min Act: -0.1700
Data Index: 2474132 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7662. Min Act: -0.1700
Data Index: 6056163 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7662. Min Act: -0.1700
Data Index: 5894940 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7662. Min Act: -0.1700
Data Index: 101041 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7349. Min Act: -0.1700
Data Index: 7849046 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.7037. Min Act: -0.1700
Data Index: 606497 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1412. Min Range: -6.1412
Max Act: 5.6724. Min Act: -0.1700
Data Index: 2227997 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19