Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0875. Min Range: -6.0875
Max Act: 6.0875. Min Act: -0.1700
Data Index: 4429669 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.8375. Min Act: -0.1700
Data Index: 1108638 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.7438. Min Act: -0.1700
Data Index: 2242004 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.6813. Min Act: -0.1700
Data Index: 2423999 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.6500. Min Act: -0.1700
Data Index: 4455301 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.6500. Min Act: -0.1700
Data Index: 4757368 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.6188. Min Act: -0.1700
Data Index: 2601645 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.5875. Min Act: -0.1700
Data Index: 5448501 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.5875. Min Act: -0.1700
Data Index: 5167382 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.5875. Min Act: -0.1700
Data Index: 1712193 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.5875. Min Act: -0.1700
Data Index: 1952195 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.5563. Min Act: -0.1700
Data Index: 5448506 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4938. Min Act: -0.1700
Data Index: 2100366 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4625. Min Act: -0.1700
Data Index: 2748323 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4625. Min Act: -0.1700
Data Index: 1712194 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4625. Min Act: -0.1700
Data Index: 5543849 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4625. Min Act: -0.1700
Data Index: 2067585 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4625. Min Act: -0.1700
Data Index: 7393736 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4625. Min Act: -0.1700
Data Index: 4879664 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0875. Min Range: -6.0875
Max Act: 5.4313. Min Act: -0.1700
Data Index: 1944256 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19