Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 467 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.5204. Min Act: -0.1700
Data Index: 2889954 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.4891. Min Act: -0.1700
Data Index: 2958666 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.4266. Min Act: -0.1700
Data Index: 3250047 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3954. Min Act: -0.1700
Data Index: 4754432 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3954. Min Act: -0.1700
Data Index: 2889951 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3954. Min Act: -0.1700
Data Index: 2233543 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3954. Min Act: -0.1700
Data Index: 1775835 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.4266. Min Act: -0.1700
Data Index: 7138834 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3954. Min Act: -0.1700
Data Index: 6673983 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3641. Min Act: -0.1700
Data Index: 5650481 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3641. Min Act: -0.1700
Data Index: 2889953 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 2124461 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 76379 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 6888636 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 5311753 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 5633216 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 2884843 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 1944814 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3016. Min Act: -0.1700
Data Index: 1594184 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5204. Min Range: -4.5204
Max Act: 4.3329. Min Act: -0.1700
Data Index: 5648780 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19