Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.4525. Min Act: -0.1700
Data Index: 4284953 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.3588. Min Act: -0.1700
Data Index: 1995212 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.3588. Min Act: -0.1700
Data Index: 7167834 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.3588. Min Act: -0.1700
Data Index: 6226594 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.3900. Min Act: -0.1700
Data Index: 4573509 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2963. Min Act: -0.1700
Data Index: 8090484 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2963. Min Act: -0.1700
Data Index: 4455002 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2963. Min Act: -0.1700
Data Index: 8205507 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2963. Min Act: -0.1700
Data Index: 6192669 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2963. Min Act: -0.1700
Data Index: 5927425 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2963. Min Act: -0.1700
Data Index: 1880322 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2338. Min Act: -0.1700
Data Index: 1380995 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2650. Min Act: -0.1700
Data Index: 4265739 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2025. Min Act: -0.1700
Data Index: 2192447 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2025. Min Act: -0.1700
Data Index: 7134847 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.1713. Min Act: -0.1700
Data Index: 563048 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.2025. Min Act: -0.1700
Data Index: 5230506 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.1713. Min Act: -0.1700
Data Index: 1728530 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.1088. Min Act: -0.1700
Data Index: 299543 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4525. Min Range: -7.4525
Max Act: 7.1088. Min Act: -0.1700
Data Index: 6242590 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19