Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.1191. Min Act: -0.1700
Data Index: 3089785 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0857. Min Act: -0.1700
Data Index: 1419096 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0689. Min Act: -0.1700
Data Index: 744370 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0689. Min Act: -0.1700
Data Index: 8631769 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0689. Min Act: -0.1700
Data Index: 3159867 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0352. Min Act: -0.1700
Data Index: 6981715 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0521. Min Act: -0.1700
Data Index: 8025428 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0352. Min Act: -0.1700
Data Index: 8631770 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0184. Min Act: -0.1700
Data Index: 3677410 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0184. Min Act: -0.1700
Data Index: 4550923 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0184. Min Act: -0.1700
Data Index: 6897010 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0184. Min Act: -0.1700
Data Index: 5650740 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0015. Min Act: -0.1700
Data Index: 5672868 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0015. Min Act: -0.1700
Data Index: 8631771 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0015. Min Act: -0.1700
Data Index: 3625918 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1191. Min Range: -2.1191
Max Act: 1.9931. Min Act: -0.1700
Data Index: 5505062 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0015. Min Act: -0.1700
Data Index: 3862406 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0015. Min Act: -0.1700
Data Index: 2838373 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1191. Min Range: -2.1191
Max Act: 1.9931. Min Act: -0.1700
Data Index: 4084860 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1191. Min Range: -2.1191
Max Act: 2.0015. Min Act: -0.1700
Data Index: 6897009 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19