Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2813. Min Range: -6.2813
Max Act: 6.2813. Min Act: -0.1700
Data Index: 2057734 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2813. Min Range: -6.2813
Max Act: 6.0313. Min Act: -0.1700
Data Index: 7776851 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2813. Min Range: -6.2813
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6388881 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.8751. Min Act: -0.1700
Data Index: 6222699 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.8438. Min Act: -0.1700
Data Index: 6206910 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.8126. Min Act: -0.1700
Data Index: 1021993 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.7813. Min Act: -0.1700
Data Index: 2299970 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.7188. Min Act: -0.1700
Data Index: 6665609 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.7188. Min Act: -0.1700
Data Index: 6929831 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.7501. Min Act: -0.1700
Data Index: 1012093 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.6876. Min Act: -0.1700
Data Index: 7966674 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.6876. Min Act: -0.1700
Data Index: 5812295 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.6563. Min Act: -0.1700
Data Index: 1584599 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.6563. Min Act: -0.1700
Data Index: 4563870 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.6251. Min Act: -0.1700
Data Index: 7229178 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.5938. Min Act: -0.1700
Data Index: 7229982 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.5626. Min Act: -0.1700
Data Index: 7567779 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.5626. Min Act: -0.1700
Data Index: 2226749 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.5626. Min Act: -0.1700
Data Index: 6929832 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2813. Min Range: -6.2813
Max Act: 5.5626. Min Act: -0.1700
Data Index: 851508 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19