Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6079. Min Range: -9.6079
Max Act: 9.6079. Min Act: -0.1700
Data Index: 4855350 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.7954. Min Act: -0.1700
Data Index: 2922034 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.6704. Min Act: -0.1700
Data Index: 3262609 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.4829. Min Act: -0.1700
Data Index: 1620851 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.5454. Min Act: -0.1700
Data Index: 4192785 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.4204. Min Act: -0.1700
Data Index: 6983667 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.4204. Min Act: -0.1700
Data Index: 5953509 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.4204. Min Act: -0.1700
Data Index: 6596494 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.3579. Min Act: -0.1700
Data Index: 7634873 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.3579. Min Act: -0.1700
Data Index: 2086235 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.3579. Min Act: -0.1700
Data Index: 6211534 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.3266. Min Act: -0.1700
Data Index: 7139501 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.2954. Min Act: -0.1700
Data Index: 7088967 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.3266. Min Act: -0.1700
Data Index: 4627629 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.2641. Min Act: -0.1700
Data Index: 2121762 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.2329. Min Act: -0.1700
Data Index: 6233483 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.2329. Min Act: -0.1700
Data Index: 520055 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.2329. Min Act: -0.1700
Data Index: 5617817 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.2641. Min Act: -0.1700
Data Index: 5202234 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6079. Min Range: -9.6079
Max Act: 8.2016. Min Act: -0.1700
Data Index: 787274 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19