Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6928. Min Act: -0.1700
Data Index: 7273725 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6303. Min Act: -0.1700
Data Index: 3212214 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5678. Min Act: -0.1700
Data Index: 7291580 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5678. Min Act: -0.1700
Data Index: 4772453 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5366. Min Act: -0.1700
Data Index: 7134360 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5366. Min Act: -0.1700
Data Index: 5492184 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5053. Min Act: -0.1700
Data Index: 5734140 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5053. Min Act: -0.1700
Data Index: 5283507 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4741. Min Act: -0.1700
Data Index: 5709752 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4741. Min Act: -0.1700
Data Index: 4800799 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4741. Min Act: -0.1700
Data Index: 5734137 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1698
Data Index: 3875682 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 2502583 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 6399634 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 3081068 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 3081062 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 4772454 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 4772455 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 7110358 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 3326107 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19