Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.9895. Min Act: -0.1700
Data Index: 6180295 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7706. Min Act: -0.1700
Data Index: 6005603 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.8019. Min Act: -0.1700
Data Index: 4265252 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7706. Min Act: -0.1700
Data Index: 1544154 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7081. Min Act: -0.1700
Data Index: 8538772 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7394. Min Act: -0.1700
Data Index: 3632558 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7081. Min Act: -0.1700
Data Index: 1230979 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7081. Min Act: -0.1700
Data Index: 6683859 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7394. Min Act: -0.1700
Data Index: 4259299 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6768. Min Act: -0.1700
Data Index: 8016113 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7081. Min Act: -0.1700
Data Index: 4134309 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6768. Min Act: -0.1700
Data Index: 4259300 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.7081. Min Act: -0.1700
Data Index: 4902424 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6768. Min Act: -0.1700
Data Index: 4888948 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6455. Min Act: -0.1700
Data Index: 4852940 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6455. Min Act: -0.1700
Data Index: 3506215 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6455. Min Act: -0.1700
Data Index: 7556265 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6455. Min Act: -0.1700
Data Index: 4709858 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6299. Min Act: -0.1700
Data Index: 5542690 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9895. Min Range: -3.9895
Max Act: 3.6455. Min Act: -0.1700
Data Index: 6489200 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19