Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2131 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.7635. Min Act: -0.1700
Data Index: 4616048 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.5135. Min Act: -0.1700
Data Index: 5057639 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.3885. Min Act: -0.1700
Data Index: 6178434 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.3260. Min Act: -0.1700
Data Index: 1057956 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.2010. Min Act: -0.1700
Data Index: 3978870 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.2323. Min Act: -0.1700
Data Index: 4465417 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.2010. Min Act: -0.1700
Data Index: 1111072 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.1698. Min Act: -0.1700
Data Index: 3841639 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.0760. Min Act: -0.1700
Data Index: 6750011 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.1385. Min Act: -0.1700
Data Index: 6973373 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.1385. Min Act: -0.1700
Data Index: 7295472 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.1073. Min Act: -0.1700
Data Index: 579887 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.0760. Min Act: -0.1700
Data Index: 8134774 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.1073. Min Act: -0.1700
Data Index: 6591725 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.0760. Min Act: -0.1700
Data Index: 8697395 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.1073. Min Act: -0.1700
Data Index: 7114589 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.0448. Min Act: -0.1700
Data Index: 156886 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.0448. Min Act: -0.1700
Data Index: 5677157 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.0135. Min Act: -0.1700
Data Index: 5794155 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7635. Min Range: -7.7635
Max Act: 7.0135. Min Act: -0.1700
Data Index: 8719560 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19