Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.7718. Min Act: -0.1700
Data Index: 7433573 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.7079. Min Act: -0.1700
Data Index: 1809199 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.6919. Min Act: -0.1700
Data Index: 7433572 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.6759. Min Act: -0.1700
Data Index: 1035395 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.6759. Min Act: -0.1700
Data Index: 1293009 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.6438. Min Act: -0.1700
Data Index: 4606205 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.6438. Min Act: -0.1700
Data Index: 1804638 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.6438. Min Act: -0.1700
Data Index: 2939750 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.6117. Min Act: -0.1700
Data Index: 539266 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5795. Min Act: -0.1700
Data Index: 2312082 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5795. Min Act: -0.1700
Data Index: 1153106 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5956. Min Act: -0.1700
Data Index: 69776 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5795. Min Act: -0.1700
Data Index: 1506811 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5634. Min Act: -0.1700
Data Index: 7864951 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5634. Min Act: -0.1700
Data Index: 4016854 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5634. Min Act: -0.1700
Data Index: 281552 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5634. Min Act: -0.1700
Data Index: 18243 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5634. Min Act: -0.1700
Data Index: 4255606 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5634. Min Act: -0.1700
Data Index: 4172082 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7718. Min Range: -2.7718
Max Act: 2.5634. Min Act: -0.1700
Data Index: 5682394 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19