Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7414. Min Range: -8.7414
Max Act: 8.7414. Min Act: -0.1700
Data Index: 7876368 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7414. Min Range: -8.7414
Max Act: 8.4914. Min Act: -0.1700
Data Index: 2044742 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7414. Min Range: -8.7414
Max Act: 8.1789. Min Act: -0.1700
Data Index: 8288270 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7414. Min Range: -8.7414
Max Act: 8.1789. Min Act: -0.1700
Data Index: 8585408 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7414. Min Range: -8.7414
Max Act: 8.0539. Min Act: -0.1700
Data Index: 3835538 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7414. Min Range: -8.7414
Max Act: 8.0539. Min Act: -0.1700
Data Index: 3206305 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9914. Min Act: -0.1700
Data Index: 771062 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9914. Min Act: -0.1700
Data Index: 8695314 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9914. Min Act: -0.1700
Data Index: 8654302 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7414. Min Range: -8.7414
Max Act: 8.0539. Min Act: -0.1700
Data Index: 1728291 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9289. Min Act: -0.1700
Data Index: 1729802 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9289. Min Act: -0.1700
Data Index: 6430467 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9289. Min Act: -0.1700
Data Index: 7710230 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9289. Min Act: -0.1700
Data Index: 5107053 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9289. Min Act: -0.1700
Data Index: 1224974 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.9289. Min Act: -0.1700
Data Index: 4537661 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.8664. Min Act: -0.1700
Data Index: 5117707 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.8664. Min Act: -0.1700
Data Index: 141492 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.8039. Min Act: -0.1700
Data Index: 1445084 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7414. Min Range: -8.7414
Max Act: 7.8664. Min Act: -0.1700
Data Index: 3773257 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19