Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2492 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5109. Min Range: -12.5109
Max Act: 12.5109. Min Act: -0.1700
Data Index: 4054455 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5109. Min Range: -12.5109
Max Act: 12.0734. Min Act: -0.1700
Data Index: 2750574 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5109. Min Range: -12.5109
Max Act: 12.0109. Min Act: -0.1700
Data Index: 7504992 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.9484. Min Act: -0.1700
Data Index: 2073206 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5109. Min Range: -12.5109
Max Act: 12.0734. Min Act: -0.1700
Data Index: 7024942 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.9484. Min Act: -0.1700
Data Index: 80883 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.8859. Min Act: -0.1700
Data Index: 1560606 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.9484. Min Act: -0.1700
Data Index: 5087548 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.8859. Min Act: -0.1700
Data Index: 8221660 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.8234. Min Act: -0.1700
Data Index: 7143308 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.8234. Min Act: -0.1700
Data Index: 456891 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.8234. Min Act: -0.1700
Data Index: 8239771 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.7609. Min Act: -0.1700
Data Index: 8052869 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.7609. Min Act: -0.1700
Data Index: 360533 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.6984. Min Act: -0.1700
Data Index: 2906751 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.6984. Min Act: -0.1700
Data Index: 7726893 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.6984. Min Act: -0.1700
Data Index: 3739508 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.6984. Min Act: -0.1700
Data Index: 2220648 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.6359. Min Act: -0.1700
Data Index: 6950764 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5109. Min Range: -12.5109
Max Act: 11.6984. Min Act: -0.1700
Data Index: 4226278 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19