Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1096. Min Range: -7.1096
Max Act: 7.1096. Min Act: -0.1700
Data Index: 770744 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1096. Min Range: -7.1096
Max Act: 7.0783. Min Act: -0.1700
Data Index: 5122346 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1096. Min Range: -7.1096
Max Act: 7.0471. Min Act: -0.1700
Data Index: 4312719 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1096. Min Range: -7.1096
Max Act: 7.0471. Min Act: -0.1700
Data Index: 6712252 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.9533. Min Act: -0.1700
Data Index: 6550978 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.9533. Min Act: -0.1700
Data Index: 7391505 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.9221. Min Act: -0.1700
Data Index: 7360000 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.8596. Min Act: -0.1700
Data Index: 8507622 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.8596. Min Act: -0.1700
Data Index: 5440356 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.8596. Min Act: -0.1700
Data Index: 3861077 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.8283. Min Act: -0.1700
Data Index: 2244515 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.8283. Min Act: -0.1700
Data Index: 5630706 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7658. Min Act: -0.1700
Data Index: 6127780 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7971. Min Act: -0.1700
Data Index: 7225158 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7971. Min Act: -0.1700
Data Index: 5669058 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7971. Min Act: -0.1700
Data Index: 7624333 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7658. Min Act: -0.1700
Data Index: 1980359 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7658. Min Act: -0.1700
Data Index: 2631573 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7033. Min Act: -0.1700
Data Index: 6888631 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1096. Min Range: -7.1096
Max Act: 6.7346. Min Act: -0.1700
Data Index: 2492417 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19