Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6371 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.7990. Min Act: -0.1700
Data Index: 6054774 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.5803. Min Act: -0.1700
Data Index: 5132263 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.5490. Min Act: -0.1700
Data Index: 7143609 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.5178. Min Act: -0.1700
Data Index: 6752372 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.2365. Min Act: -0.1700
Data Index: 2814068 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.2365. Min Act: -0.1700
Data Index: 5629658 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.2365. Min Act: -0.1700
Data Index: 4385398 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.2365. Min Act: -0.1700
Data Index: 2635632 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1740. Min Act: -0.1700
Data Index: 5775379 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.2053. Min Act: -0.1700
Data Index: 2800705 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1115. Min Act: -0.1700
Data Index: 439847 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1740. Min Act: -0.1700
Data Index: 5233905 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1428. Min Act: -0.1700
Data Index: 327166 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1115. Min Act: -0.1700
Data Index: 7116198 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1115. Min Act: -0.1700
Data Index: 4521940 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1115. Min Act: -0.1700
Data Index: 1753982 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.1428. Min Act: -0.1700
Data Index: 5423155 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.0803. Min Act: -0.1700
Data Index: 1649097 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.0803. Min Act: -0.1700
Data Index: 962558 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7990. Min Range: -6.7990
Max Act: 6.0490. Min Act: -0.1700
Data Index: 813010 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19