Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.7353. Min Act: -0.1700
Data Index: 2378046 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.2353. Min Act: -0.1700
Data Index: 7453793 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.1103. Min Act: -0.1700
Data Index: 2781609 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7353. Min Range: -5.7353
Max Act: 5.0478. Min Act: -0.1700
Data Index: 54410 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9853. Min Act: -0.1700
Data Index: 1353442 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9853. Min Act: -0.1700
Data Index: 5222580 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9540. Min Act: -0.1700
Data Index: 5419701 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9540. Min Act: -0.1700
Data Index: 8171876 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.8915. Min Act: -0.1700
Data Index: 2837188 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9228. Min Act: -0.1700
Data Index: 5882651 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9228. Min Act: -0.1700
Data Index: 6978457 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.8915. Min Act: -0.1700
Data Index: 3323805 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.8915. Min Act: -0.1700
Data Index: 3071240 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.9228. Min Act: -0.1700
Data Index: 7678792 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.8603. Min Act: -0.1700
Data Index: 3256516 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.8603. Min Act: -0.1700
Data Index: 6956425 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.8915. Min Act: -0.1700
Data Index: 6969507 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.7978. Min Act: -0.1700
Data Index: 6689884 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.7978. Min Act: -0.1700
Data Index: 7381068 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7353. Min Range: -5.7353
Max Act: 4.7978. Min Act: -0.1700
Data Index: 52548 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19