Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.5642. Min Act: -0.1700
Data Index: 6026403 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.5642. Min Act: -0.1700
Data Index: 6615818 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.4704. Min Act: -0.1700
Data Index: 5360341 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3767. Min Act: -0.1700
Data Index: 1449818 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3767. Min Act: -0.1700
Data Index: 8794177 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3767. Min Act: -0.1700
Data Index: 4224663 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3767. Min Act: -0.1700
Data Index: 4728577 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3767. Min Act: -0.1700
Data Index: 1287599 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3454. Min Act: -0.1700
Data Index: 5856425 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3142. Min Act: -0.1700
Data Index: 198700 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3454. Min Act: -0.1700
Data Index: 8299457 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3454. Min Act: -0.1700
Data Index: 7546869 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3454. Min Act: -0.1700
Data Index: 785231 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3142. Min Act: -0.1700
Data Index: 4477120 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3454. Min Act: -0.1700
Data Index: 349895 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.3142. Min Act: -0.1700
Data Index: 250716 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.2829. Min Act: -0.1700
Data Index: 6770777 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.2517. Min Act: -0.1700
Data Index: 4871 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.2517. Min Act: -0.1700
Data Index: 6995117 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5642. Min Range: -5.5642
Max Act: 5.2829. Min Act: -0.1700
Data Index: 4741030 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19