Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1728. Min Range: -6.1728
Max Act: 6.1728. Min Act: -0.1700
Data Index: 1752362 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1728. Min Range: -6.1728
Max Act: 6.1415. Min Act: -0.1700
Data Index: 8174630 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1728. Min Range: -6.1728
Max Act: 6.0478. Min Act: -0.1700
Data Index: 87394 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1728. Min Range: -6.1728
Max Act: 6.0165. Min Act: -0.1700
Data Index: 3215043 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.9853. Min Act: -0.1700
Data Index: 2827067 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.9540. Min Act: -0.1700
Data Index: 6021639 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.9228. Min Act: -0.1700
Data Index: 411245 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.8915. Min Act: -0.1700
Data Index: 8266524 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.8603. Min Act: -0.1700
Data Index: 5482920 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.8290. Min Act: -0.1700
Data Index: 6159892 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.8290. Min Act: -0.1700
Data Index: 433314 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.8290. Min Act: -0.1700
Data Index: 5561432 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.8290. Min Act: -0.1700
Data Index: 5869866 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.7665. Min Act: -0.1700
Data Index: 8175389 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.7353. Min Act: -0.1700
Data Index: 1793886 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.7353. Min Act: -0.1700
Data Index: 4725543 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.7353. Min Act: -0.1700
Data Index: 8011283 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.7040. Min Act: -0.1700
Data Index: 1925824 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.6728. Min Act: -0.1700
Data Index: 3822299 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1728. Min Range: -6.1728
Max Act: 5.6728. Min Act: -0.1700
Data Index: 915562 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19