Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4927 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.9294. Min Act: -0.1700
Data Index: 3217947 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.9294. Min Act: -0.1700
Data Index: 5157867 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.8669. Min Act: -0.1700
Data Index: 903765 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.8043. Min Act: -0.1700
Data Index: 7330594 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.7261. Min Act: -0.1700
Data Index: 8790811 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.7261. Min Act: -0.1700
Data Index: 859559 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.6948. Min Act: -0.1700
Data Index: 3217948 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.6636. Min Act: -0.1700
Data Index: 944995 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.6166. Min Act: -0.1700
Data Index: 4157472 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.6010. Min Act: -0.1700
Data Index: 4908547 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.5853. Min Act: -0.1700
Data Index: 7954815 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.5853. Min Act: -0.1700
Data Index: 4385673 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.5540. Min Act: -0.1700
Data Index: 7427433 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.5540. Min Act: -0.1700
Data Index: 4613288 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.5383. Min Act: -0.1700
Data Index: 4308803 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.5383. Min Act: -0.1700
Data Index: 8479796 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.5070. Min Act: -0.1700
Data Index: 8552171 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.4600. Min Act: -0.1700
Data Index: 434416 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.4757. Min Act: -0.1700
Data Index: 5689316 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9294. Min Range: -3.9294
Max Act: 3.4757. Min Act: -0.1700
Data Index: 109684 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19