Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2178. Min Range: -5.2178
Max Act: 5.2178. Min Act: -0.1700
Data Index: 4812257 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2178. Min Range: -5.2178
Max Act: 5.1866. Min Act: -0.1700
Data Index: 388388 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2178. Min Range: -5.2178
Max Act: 5.0928. Min Act: -0.1700
Data Index: 1916375 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2178. Min Range: -5.2178
Max Act: 5.1241. Min Act: -0.1700
Data Index: 3778930 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2178. Min Range: -5.2178
Max Act: 5.0616. Min Act: -0.1700
Data Index: 8419540 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9991. Min Act: -0.1700
Data Index: 3658489 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2178. Min Range: -5.2178
Max Act: 5.0303. Min Act: -0.1700
Data Index: 7006960 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9991. Min Act: -0.1700
Data Index: 2292457 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2178. Min Range: -5.2178
Max Act: 5.0616. Min Act: -0.1700
Data Index: 5808846 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9991. Min Act: -0.1700
Data Index: 3869 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9678. Min Act: -0.1700
Data Index: 5405066 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9678. Min Act: -0.1700
Data Index: 3855719 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9678. Min Act: -0.1700
Data Index: 5689071 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9366. Min Act: -0.1700
Data Index: 7732166 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9678. Min Act: -0.1700
Data Index: 4317469 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9678. Min Act: -0.1700
Data Index: 6785297 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9366. Min Act: -0.1700
Data Index: 5839893 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9366. Min Act: -0.1700
Data Index: 540437 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.9053. Min Act: -0.1700
Data Index: 3704060 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2178. Min Range: -5.2178
Max Act: 4.8741. Min Act: -0.1700
Data Index: 4559593 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19