Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2032 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0393. Min Range: -4.0393
Max Act: 4.0393. Min Act: -0.1700
Data Index: 3920085 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0393. Min Range: -4.0393
Max Act: 4.0393. Min Act: -0.1700
Data Index: 7843367 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0393. Min Range: -4.0393
Max Act: 4.0393. Min Act: -0.1700
Data Index: 8615096 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0393. Min Range: -4.0393
Max Act: 4.0081. Min Act: -0.1700
Data Index: 5833958 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.9768. Min Act: -0.1700
Data Index: 2391753 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.9768. Min Act: -0.1700
Data Index: 5889580 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.9455. Min Act: -0.1700
Data Index: 5382885 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.9455. Min Act: -0.1700
Data Index: 5480606 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.9143. Min Act: -0.1700
Data Index: 8260244 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.9143. Min Act: -0.1700
Data Index: 6254062 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8830. Min Act: -0.1700
Data Index: 6804095 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8830. Min Act: -0.1700
Data Index: 4546030 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8830. Min Act: -0.1700
Data Index: 6525869 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8830. Min Act: -0.1700
Data Index: 2823489 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8830. Min Act: -0.1700
Data Index: 700864 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8830. Min Act: -0.1700
Data Index: 5805442 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8830. Min Act: -0.1700
Data Index: 4959894 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8517. Min Act: -0.1700
Data Index: 5536722 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.8205. Min Act: -0.1700
Data Index: 1063762 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0393. Min Range: -4.0393
Max Act: 3.7892. Min Act: -0.1700
Data Index: 2313665 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19