Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1526 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.6805. Min Act: -0.1700
Data Index: 2598833 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.6180. Min Act: -0.1700
Data Index: 4511782 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.3367. Min Act: -0.1700
Data Index: 6727424 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.3680. Min Act: -0.1700
Data Index: 3235939 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.3055. Min Act: -0.1700
Data Index: 1859058 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.1805. Min Act: -0.1700
Data Index: 5096034 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.2117. Min Act: -0.1700
Data Index: 565711 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.1805. Min Act: -0.1700
Data Index: 5821739 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.1492. Min Act: -0.1700
Data Index: 3441817 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0867. Min Act: -0.1700
Data Index: 3031298 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0867. Min Act: -0.1700
Data Index: 8045558 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.1180. Min Act: -0.1700
Data Index: 361398 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0867. Min Act: -0.1700
Data Index: 8034448 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0867. Min Act: -0.1700
Data Index: 673017 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0867. Min Act: -0.1700
Data Index: 4028031 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0555. Min Act: -0.1700
Data Index: 660568 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0555. Min Act: -0.1700
Data Index: 5215786 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0555. Min Act: -0.1700
Data Index: 3274043 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0555. Min Act: -0.1700
Data Index: 1994802 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6805. Min Range: -5.6805
Max Act: 5.0555. Min Act: -0.1700
Data Index: 5218481 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19