Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4555 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.2488. Min Act: -0.1700
Data Index: 7184259 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1863. Min Act: -0.1700
Data Index: 37511 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1551. Min Act: -0.1700
Data Index: 5480137 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1551. Min Act: -0.1700
Data Index: 1451392 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 4786412 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0926. Min Act: -0.1700
Data Index: 3217609 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 5418257 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 4685306 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 8501785 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1238. Min Act: -0.1700
Data Index: 4786415 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.1551. Min Act: -0.1700
Data Index: 231038 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0926. Min Act: -0.1700
Data Index: 3548835 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0926. Min Act: -0.1700
Data Index: 605460 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0926. Min Act: -0.1700
Data Index: 1352763 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0926. Min Act: -0.1700
Data Index: 6717111 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0613. Min Act: -0.1700
Data Index: 700761 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0613. Min Act: -0.1700
Data Index: 5498302 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0926. Min Act: -0.1700
Data Index: 725971 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0613. Min Act: -0.1700
Data Index: 7545417 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2488. Min Range: -5.2488
Max Act: 5.0613. Min Act: -0.1700
Data Index: 8497164 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19