Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5257 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.7598. Min Act: -0.1700
Data Index: 2000310 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.6035. Min Act: -0.1700
Data Index: 635642 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.6035. Min Act: -0.1700
Data Index: 8178794 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5723. Min Act: -0.1700
Data Index: 3025033 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5410. Min Act: -0.1700
Data Index: 7024536 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5410. Min Act: -0.1700
Data Index: 3168133 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5098. Min Act: -0.1700
Data Index: 2056995 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5410. Min Act: -0.1700
Data Index: 7623357 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5410. Min Act: -0.1700
Data Index: 6682827 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5098. Min Act: -0.1700
Data Index: 3256155 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5098. Min Act: -0.1700
Data Index: 2194448 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.4785. Min Act: -0.1700
Data Index: 27626 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5098. Min Act: -0.1700
Data Index: 2770891 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5098. Min Act: -0.1700
Data Index: 7067008 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.4785. Min Act: -0.1700
Data Index: 5281399 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.5098. Min Act: -0.1700
Data Index: 8284485 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.4473. Min Act: -0.1700
Data Index: 3794505 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.4785. Min Act: -0.1700
Data Index: 7213945 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.4785. Min Act: -0.1700
Data Index: 2407034 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7598. Min Range: -4.7598
Max Act: 4.4785. Min Act: -0.1700
Data Index: 8387448 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19