Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1417. Min Range: -3.1417
Max Act: 3.1417. Min Act: -0.1700
Data Index: 6260194 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1417. Min Range: -3.1417
Max Act: 3.1259. Min Act: -0.1700
Data Index: 2415429 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1417. Min Range: -3.1417
Max Act: 3.0155. Min Act: -0.1700
Data Index: 4485748 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.9681. Min Act: -0.1700
Data Index: 4588047 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.9681. Min Act: -0.1700
Data Index: 6496307 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.9523. Min Act: -0.1700
Data Index: 987395 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8730. Min Act: -0.1700
Data Index: 7554106 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8889. Min Act: -0.1700
Data Index: 4621307 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8730. Min Act: -0.1700
Data Index: 5751815 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8730. Min Act: -0.1700
Data Index: 6267062 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8571. Min Act: -0.1700
Data Index: 4186980 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8889. Min Act: -0.1700
Data Index: 2966167 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8730. Min Act: -0.1700
Data Index: 2716774 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8730. Min Act: -0.1700
Data Index: 5379460 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8571. Min Act: -0.1700
Data Index: 6344436 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8730. Min Act: -0.1700
Data Index: 4610686 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8571. Min Act: -0.1700
Data Index: 5454605 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8571. Min Act: -0.1700
Data Index: 3835243 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8730. Min Act: -0.1700
Data Index: 3274014 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1417. Min Range: -3.1417
Max Act: 2.8571. Min Act: -0.1700
Data Index: 3051635 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19