Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.8771. Min Act: -0.1700
Data Index: 1059636 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.8302. Min Act: -0.1700
Data Index: 4946831 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7989. Min Act: -0.1700
Data Index: 1756307 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7676. Min Act: -0.1700
Data Index: 2427578 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7989. Min Act: -0.1700
Data Index: 3133393 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7676. Min Act: -0.1700
Data Index: 5713422 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7676. Min Act: -0.1700
Data Index: 346902 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7520. Min Act: -0.1700
Data Index: 7129271 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7520. Min Act: -0.1700
Data Index: 512632 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7207. Min Act: -0.1700
Data Index: 2556596 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7363. Min Act: -0.1700
Data Index: 3215682 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7050. Min Act: -0.1700
Data Index: 3241256 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.7050. Min Act: -0.1700
Data Index: 5915429 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.6894. Min Act: -0.1700
Data Index: 6052376 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.6738. Min Act: -0.1700
Data Index: 495814 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.6425. Min Act: -0.1700
Data Index: 1651022 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.6581. Min Act: -0.1700
Data Index: 7245799 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.6581. Min Act: -0.1700
Data Index: 5369741 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.6268. Min Act: -0.1700
Data Index: 5450481 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8771. Min Range: -3.8771
Max Act: 3.6268. Min Act: -0.1700
Data Index: 7090686 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19