Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.3626. Min Act: -0.1700
Data Index: 8053400 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.3155. Min Act: -0.1700
Data Index: 5502166 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.2527. Min Act: -0.1700
Data Index: 2195927 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.2055. Min Act: -0.1700
Data Index: 2871632 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.2213. Min Act: -0.1700
Data Index: 215136 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1741. Min Act: -0.1700
Data Index: 7277914 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1426. Min Act: -0.1700
Data Index: 2795764 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1583. Min Act: -0.1700
Data Index: 6741947 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1426. Min Act: -0.1700
Data Index: 2195929 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1583. Min Act: -0.1700
Data Index: 149048 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1741. Min Act: -0.1700
Data Index: 4160163 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1583. Min Act: -0.1700
Data Index: 2795765 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1583. Min Act: -0.1700
Data Index: 4080883 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1426. Min Act: -0.1700
Data Index: 4563961 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1426. Min Act: -0.1700
Data Index: 3728275 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1583. Min Act: -0.1700
Data Index: 3565563 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1269. Min Act: -0.1700
Data Index: 2795770 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1269. Min Act: -0.1700
Data Index: 2822379 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1111. Min Act: -0.1700
Data Index: 7691100 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3626. Min Range: -3.3626
Max Act: 3.1111. Min Act: -0.1700
Data Index: 6270039 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19