Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.9501. Min Act: -0.1700
Data Index: 5869121 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.8563. Min Act: -0.1700
Data Index: 5047870 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.7938. Min Act: -0.1700
Data Index: 8130272 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.7626. Min Act: -0.1700
Data Index: 7076754 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.6376. Min Act: -0.1700
Data Index: 3343791 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.7001. Min Act: -0.1700
Data Index: 657050 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.6063. Min Act: -0.1700
Data Index: 6889264 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.6376. Min Act: -0.1700
Data Index: 7993568 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.5751. Min Act: -0.1700
Data Index: 5253385 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.5126. Min Act: -0.1700
Data Index: 6705057 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.5126. Min Act: -0.1700
Data Index: 4611082 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.5438. Min Act: -0.1700
Data Index: 4498149 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4813. Min Act: -0.1700
Data Index: 1071309 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4813. Min Act: -0.1700
Data Index: 1140246 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4501. Min Act: -0.1700
Data Index: 8409449 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4188. Min Act: -0.1700
Data Index: 550079 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4188. Min Act: -0.1700
Data Index: 2286884 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4501. Min Act: -0.1700
Data Index: 1791896 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4188. Min Act: -0.1700
Data Index: 4132549 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9501. Min Range: -6.9501
Max Act: 6.4188. Min Act: -0.1700
Data Index: 3384368 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19