Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2122 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2014. Min Range: -6.2014
Max Act: 6.2014. Min Act: -0.1700
Data Index: 5401203 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.8577. Min Act: -0.1700
Data Index: 2064692 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.8264. Min Act: -0.1700
Data Index: 1603383 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.7327. Min Act: -0.1700
Data Index: 7883166 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.6702. Min Act: -0.1700
Data Index: 1285560 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.5764. Min Act: -0.1700
Data Index: 270463 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.4827. Min Act: -0.1700
Data Index: 6434179 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.4827. Min Act: -0.1700
Data Index: 6434174 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.3889. Min Act: -0.1700
Data Index: 4860368 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.3889. Min Act: -0.1700
Data Index: 6434187 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.3889. Min Act: -0.1700
Data Index: 520913 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.3577. Min Act: -0.1700
Data Index: 6434181 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.3264. Min Act: -0.1700
Data Index: 7310922 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.2952. Min Act: -0.1700
Data Index: 2042574 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.2952. Min Act: -0.1700
Data Index: 4860377 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.2639. Min Act: -0.1700
Data Index: 6434158 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.2639. Min Act: -0.1700
Data Index: 6372441 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.2639. Min Act: -0.1700
Data Index: 1119592 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.2639. Min Act: -0.1700
Data Index: 8711878 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2014. Min Range: -6.2014
Max Act: 5.2327. Min Act: -0.1700
Data Index: 7011503 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19