Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2485. Min Range: -4.2485
Max Act: 4.2485. Min Act: -0.1700
Data Index: 7668122 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2485. Min Range: -4.2485
Max Act: 4.2172. Min Act: -0.1700
Data Index: 7151884 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2485. Min Range: -4.2485
Max Act: 4.1547. Min Act: -0.1700
Data Index: 818867 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2485. Min Range: -4.2485
Max Act: 4.0922. Min Act: -0.1700
Data Index: 162447 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2485. Min Range: -4.2485
Max Act: 4.0610. Min Act: -0.1700
Data Index: 702354 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2485. Min Range: -4.2485
Max Act: 4.0297. Min Act: -0.1700
Data Index: 2112493 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2485. Min Range: -4.2485
Max Act: 4.0297. Min Act: -0.1700
Data Index: 8313476 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9984. Min Act: -0.1700
Data Index: 5582893 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9984. Min Act: -0.1700
Data Index: 6187162 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9984. Min Act: -0.1700
Data Index: 4518110 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9672. Min Act: -0.1700
Data Index: 4966908 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9359. Min Act: -0.1700
Data Index: 5480216 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9047. Min Act: -0.1700
Data Index: 5195688 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9359. Min Act: -0.1700
Data Index: 3758356 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9047. Min Act: -0.1700
Data Index: 6174851 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.8734. Min Act: -0.1700
Data Index: 8777688 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9359. Min Act: -0.1700
Data Index: 444601 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.9047. Min Act: -0.1700
Data Index: 4031536 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.8734. Min Act: -0.1700
Data Index: 8290881 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2485. Min Range: -4.2485
Max Act: 3.8734. Min Act: -0.1700
Data Index: 2319248 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19