Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 888 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.8235. Min Act: -0.1700
Data Index: 6692953 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.7610. Min Act: -0.1700
Data Index: 4995363 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.7298. Min Act: -0.1700
Data Index: 3869147 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6985. Min Act: -0.1700
Data Index: 2841802 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6985. Min Act: -0.1700
Data Index: 5493610 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6673. Min Act: -0.1700
Data Index: 4212281 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6673. Min Act: -0.1700
Data Index: 6341184 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6673. Min Act: -0.1700
Data Index: 2449213 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6360. Min Act: -0.1700
Data Index: 198172 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6048. Min Act: -0.1700
Data Index: 1575074 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6360. Min Act: -0.1700
Data Index: 1708936 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6048. Min Act: -0.1700
Data Index: 5106869 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.5735. Min Act: -0.1700
Data Index: 2581654 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.5735. Min Act: -0.1700
Data Index: 6158310 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.6048. Min Act: -0.1700
Data Index: 5278866 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.5735. Min Act: -0.1700
Data Index: 5210176 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.5735. Min Act: -0.1700
Data Index: 5492554 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.5735. Min Act: -0.1700
Data Index: 3304182 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.5735. Min Act: -0.1700
Data Index: 4995361 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8235. Min Range: -4.8235
Max Act: 4.5735. Min Act: -0.1700
Data Index: 1313978 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19