Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5742. Min Range: -8.5742
Max Act: 8.5742. Min Act: -0.1700
Data Index: 7070764 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5742. Min Range: -8.5742
Max Act: 8.5117. Min Act: -0.1700
Data Index: 1958069 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5742. Min Range: -8.5742
Max Act: 8.1992. Min Act: -0.1700
Data Index: 3747927 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5742. Min Range: -8.5742
Max Act: 8.0742. Min Act: -0.1700
Data Index: 4964554 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5742. Min Range: -8.5742
Max Act: 8.0117. Min Act: -0.1700
Data Index: 8766565 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.9492. Min Act: -0.1700
Data Index: 4557884 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5742. Min Range: -8.5742
Max Act: 8.0117. Min Act: -0.1700
Data Index: 7286552 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.9492. Min Act: -0.1700
Data Index: 5305339 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.9492. Min Act: -0.1700
Data Index: 8402726 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8867. Min Act: -0.1700
Data Index: 2549808 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8867. Min Act: -0.1699
Data Index: 1095120 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8242. Min Act: -0.1700
Data Index: 7004195 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8242. Min Act: -0.1700
Data Index: 6838317 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8242. Min Act: -0.1700
Data Index: 6534270 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8242. Min Act: -0.1700
Data Index: 6237339 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.7617. Min Act: -0.1700
Data Index: 2627516 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8242. Min Act: -0.1700
Data Index: 6113458 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.7617. Min Act: -0.1700
Data Index: 936536 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.8242. Min Act: -0.1700
Data Index: 1525244 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5742. Min Range: -8.5742
Max Act: 7.6992. Min Act: -0.1698
Data Index: 2235968 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19