Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5500 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.2583. Min Act: -0.1700
Data Index: 3547060 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.2583. Min Act: -0.1700
Data Index: 7911873 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.1333. Min Act: -0.1700
Data Index: 3564627 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0708. Min Act: -0.1700
Data Index: 8733403 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2583. Min Range: -5.2583
Max Act: 5.0395. Min Act: -0.1700
Data Index: 935011 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.9458. Min Act: -0.1700
Data Index: 7688694 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.9458. Min Act: -0.1700
Data Index: 8177400 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.9458. Min Act: -0.1700
Data Index: 3092290 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.9458. Min Act: -0.1700
Data Index: 5731938 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.8520. Min Act: -0.1700
Data Index: 5185724 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.8520. Min Act: -0.1700
Data Index: 764847 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.8520. Min Act: -0.1700
Data Index: 6392368 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.8208. Min Act: -0.1700
Data Index: 935018 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.8208. Min Act: -0.1700
Data Index: 7271807 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.8208. Min Act: -0.1700
Data Index: 7659488 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.7583. Min Act: -0.1700
Data Index: 3045496 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.7895. Min Act: -0.1700
Data Index: 7895642 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.7583. Min Act: -0.1700
Data Index: 3810462 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.7583. Min Act: -0.1700
Data Index: 4771711 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2583. Min Range: -5.2583
Max Act: 4.7270. Min Act: -0.1700
Data Index: 1587128 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19