Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5437. Min Range: -6.5437
Max Act: 6.5437. Min Act: -0.1700
Data Index: 2796500 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5437. Min Range: -6.5437
Max Act: 6.0125. Min Act: -0.1700
Data Index: 4766351 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5437. Min Range: -6.5437
Max Act: 6.0125. Min Act: -0.1700
Data Index: 4909851 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5437. Min Range: -6.5437
Max Act: 6.0437. Min Act: -0.1700
Data Index: 1716074 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.9812. Min Act: -0.1700
Data Index: 3919240 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.9500. Min Act: -0.1700
Data Index: 6464463 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.9187. Min Act: -0.1700
Data Index: 2702013 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.9187. Min Act: -0.1700
Data Index: 3846152 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.9187. Min Act: -0.1700
Data Index: 3534915 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.8875. Min Act: -0.1700
Data Index: 5168182 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.8562. Min Act: -0.1700
Data Index: 8457853 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.8875. Min Act: -0.1700
Data Index: 1150573 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.8875. Min Act: -0.1700
Data Index: 2058346 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.8562. Min Act: -0.1700
Data Index: 5298082 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.7937. Min Act: -0.1700
Data Index: 7240308 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.8250. Min Act: -0.1700
Data Index: 2837881 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.7625. Min Act: -0.1700
Data Index: 261119 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.7625. Min Act: -0.1700
Data Index: 7056288 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.7625. Min Act: -0.1700
Data Index: 7598947 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5437. Min Range: -6.5437
Max Act: 5.7625. Min Act: -0.1700
Data Index: 5529109 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19