Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0750. Min Range: -8.0750
Max Act: 8.0750. Min Act: -0.1700
Data Index: 8607614 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0750. Min Range: -8.0750
Max Act: 8.0750. Min Act: -0.1700
Data Index: 7290770 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0750. Min Range: -8.0750
Max Act: 8.0125. Min Act: -0.1700
Data Index: 3135811 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.8875. Min Act: -0.1700
Data Index: 7805648 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7625. Min Act: -0.1700
Data Index: 2902017 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7625. Min Act: -0.1700
Data Index: 2795982 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7625. Min Act: -0.1700
Data Index: 541151 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7625. Min Act: -0.1700
Data Index: 6998294 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7625. Min Act: -0.1700
Data Index: 1626913 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7625. Min Act: -0.1700
Data Index: 2778002 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7000. Min Act: -0.1700
Data Index: 7992716 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7000. Min Act: -0.1700
Data Index: 4016970 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7000. Min Act: -0.1700
Data Index: 5621270 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7000. Min Act: -0.1700
Data Index: 4919005 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.6375. Min Act: -0.1700
Data Index: 6556477 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.6375. Min Act: -0.1700
Data Index: 7936636 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.6375. Min Act: -0.1700
Data Index: 1528517 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.7000. Min Act: -0.1700
Data Index: 676724 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.6375. Min Act: -0.1700
Data Index: 7896289 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0750. Min Range: -8.0750
Max Act: 7.6375. Min Act: -0.1700
Data Index: 6002408 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19