Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1314 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0396. Min Range: -6.0396
Max Act: 6.0396. Min Act: -0.1700
Data Index: 3493316 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0396. Min Range: -6.0396
Max Act: 6.0083. Min Act: -0.1700
Data Index: 3471933 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.9771. Min Act: -0.1700
Data Index: 8168820 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.9458. Min Act: -0.1700
Data Index: 6593206 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.9458. Min Act: -0.1700
Data Index: 5403243 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.9146. Min Act: -0.1700
Data Index: 3402158 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7896. Min Act: -0.1700
Data Index: 4347743 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7583. Min Act: -0.1700
Data Index: 4357000 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7896. Min Act: -0.1700
Data Index: 317047 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7583. Min Act: -0.1700
Data Index: 5800668 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7271. Min Act: -0.1700
Data Index: 1709355 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7271. Min Act: -0.1700
Data Index: 3521847 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7271. Min Act: -0.1700
Data Index: 4124477 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.7271. Min Act: -0.1700
Data Index: 1804387 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.6646. Min Act: -0.1700
Data Index: 5052483 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.6333. Min Act: -0.1700
Data Index: 2943532 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.6646. Min Act: -0.1700
Data Index: 2943533 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.6646. Min Act: -0.1700
Data Index: 2510700 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.6646. Min Act: -0.1700
Data Index: 6112970 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0396. Min Range: -6.0396
Max Act: 5.6333. Min Act: -0.1700
Data Index: 501508 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19