Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4411 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1643. Min Range: -4.1643
Max Act: 4.1643. Min Act: -0.1700
Data Index: 7458850 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1643. Min Range: -4.1643
Max Act: 4.1017. Min Act: -0.1700
Data Index: 6794011 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.9767. Min Act: -0.1700
Data Index: 6334616 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1643. Min Range: -4.1643
Max Act: 4.0080. Min Act: -0.1700
Data Index: 487099 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.9454. Min Act: -0.1700
Data Index: 573569 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.9142. Min Act: -0.1700
Data Index: 6693330 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.9142. Min Act: -0.1700
Data Index: 7628604 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.9454. Min Act: -0.1700
Data Index: 4581166 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.9142. Min Act: -0.1700
Data Index: 232365 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8829. Min Act: -0.1700
Data Index: 4040498 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8829. Min Act: -0.1700
Data Index: 3115833 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8829. Min Act: -0.1700
Data Index: 7784130 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8360. Min Act: -0.1700
Data Index: 7382366 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8516. Min Act: -0.1700
Data Index: 8014683 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8516. Min Act: -0.1700
Data Index: 3194430 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8204. Min Act: -0.1700
Data Index: 6329505 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8360. Min Act: -0.1700
Data Index: 6877833 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8516. Min Act: -0.1700
Data Index: 1234634 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8360. Min Act: -0.1700
Data Index: 5299704 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8360. Min Act: -0.1700
Data Index: 2935532 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19