Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 917 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.8009. Min Act: -0.1699
Data Index: 158871 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.6759. Min Act: -0.1679
Data Index: 145011 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.4884. Min Act: -0.1700
Data Index: 4238019 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.5509. Min Act: -0.1700
Data Index: 7484034 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.3009. Min Act: -0.1699
Data Index: 3242647 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.2384. Min Act: -0.1676
Data Index: 3489348 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.1759. Min Act: -0.1645
Data Index: 4219322 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.2384. Min Act: -0.1700
Data Index: 1500484 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.1759. Min Act: -0.1641
Data Index: 5965121 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.8009. Min Range: -14.8009
Max Act: 14.0509. Min Act: -0.1693
Data Index: 2743767 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.9884. Min Act: -0.1641
Data Index: 8608912 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.8634. Min Act: -0.1693
Data Index: 2304003 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.8009. Min Act: -0.1675
Data Index: 5039077 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.7384. Min Act: -0.1691
Data Index: 2126129 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.7384. Min Act: -0.1641
Data Index: 6251215 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.7384. Min Act: -0.1700
Data Index: 5312722 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.7384. Min Act: -0.1650
Data Index: 317155 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.7384. Min Act: -0.1690
Data Index: 4310357 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.6759. Min Act: -0.1700
Data Index: 4323168 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.8009. Min Range: -14.8009
Max Act: 13.7384. Min Act: -0.1661
Data Index: 5445046 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19