Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.7406. Min Act: -0.1700
Data Index: 2521258 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.7406. Min Act: -0.1700
Data Index: 5775903 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.7094. Min Act: -0.1700
Data Index: 460222 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5844. Min Act: -0.1700
Data Index: 5241666 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.6156. Min Act: -0.1700
Data Index: 3965170 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5844. Min Act: -0.1700
Data Index: 2646020 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5844. Min Act: -0.1700
Data Index: 3528125 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5844. Min Act: -0.1700
Data Index: 6615484 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5219. Min Act: -0.1700
Data Index: 6953582 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5531. Min Act: -0.1700
Data Index: 2886315 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5531. Min Act: -0.1700
Data Index: 8757868 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5531. Min Act: -0.1700
Data Index: 8508855 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5531. Min Act: -0.1700
Data Index: 4431400 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5219. Min Act: -0.1700
Data Index: 8037284 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5219. Min Act: -0.1700
Data Index: 8093437 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5219. Min Act: -0.1700
Data Index: 2150587 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.5219. Min Act: -0.1700
Data Index: 1137063 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.4906. Min Act: -0.1700
Data Index: 8476551 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.4906. Min Act: -0.1700
Data Index: 7629660 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7406. Min Range: -4.7406
Max Act: 4.4906. Min Act: -0.1700
Data Index: 5077244 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19