Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3752. Min Range: -8.3752
Max Act: 8.3752. Min Act: -0.1700
Data Index: 1378842 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3752. Min Range: -8.3752
Max Act: 8.0627. Min Act: -0.1700
Data Index: 1718371 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3752. Min Range: -8.3752
Max Act: 8.0627. Min Act: -0.1700
Data Index: 438716 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3752. Min Range: -8.3752
Max Act: 8.0627. Min Act: -0.1700
Data Index: 8467500 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.9377. Min Act: -0.1700
Data Index: 1001507 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.9377. Min Act: -0.1700
Data Index: 4561813 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.8127. Min Act: -0.1700
Data Index: 6627007 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.8127. Min Act: -0.1700
Data Index: 8476990 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.7502. Min Act: -0.1700
Data Index: 2960846 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.7502. Min Act: -0.1700
Data Index: 2479880 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.7502. Min Act: -0.1700
Data Index: 3291118 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.7502. Min Act: -0.1700
Data Index: 216467 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.6877. Min Act: -0.1700
Data Index: 757486 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.6877. Min Act: -0.1700
Data Index: 7790322 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.6877. Min Act: -0.1700
Data Index: 1364832 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.6252. Min Act: -0.1700
Data Index: 5920760 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.6877. Min Act: -0.1700
Data Index: 6673671 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.6252. Min Act: -0.1700
Data Index: 70665 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.6252. Min Act: -0.1700
Data Index: 2254547 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3752. Min Range: -8.3752
Max Act: 7.5940. Min Act: -0.1700
Data Index: 6278277 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19