Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5097 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2919. Min Range: -5.2919
Max Act: 5.2919. Min Act: -0.1700
Data Index: 3701896 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 884853 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9481. Min Act: -0.1700
Data Index: 49549 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.9794. Min Act: -0.1700
Data Index: 6791036 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.8856. Min Act: -0.1700
Data Index: 5643820 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.8231. Min Act: -0.1700
Data Index: 5997528 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.8544. Min Act: -0.1700
Data Index: 5839313 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.8544. Min Act: -0.1700
Data Index: 8599181 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 8417776 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.8544. Min Act: -0.1700
Data Index: 1682004 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7919. Min Act: -0.1700
Data Index: 93520 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 1016113 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 6707457 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 1186916 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 5787330 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7606. Min Act: -0.1700
Data Index: 4482345 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 6660981 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.7294. Min Act: -0.1700
Data Index: 6359747 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 3964915 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2919. Min Range: -5.2919
Max Act: 4.6981. Min Act: -0.1700
Data Index: 8415513 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19