Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.2414. Min Act: -0.1700
Data Index: 358407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.1789. Min Act: -0.1699
Data Index: 6223940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.1789. Min Act: -0.1700
Data Index: 4555639 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.1789. Min Act: -0.1700
Data Index: 8123553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.0851. Min Act: -0.1700
Data Index: 1290045 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.0851. Min Act: -0.1700
Data Index: 1281942 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.0226. Min Act: -0.1699
Data Index: 6317189 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2414. Min Range: -5.2414
Max Act: 5.0539. Min Act: -0.1700
Data Index: 2041923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9914. Min Act: -0.1700
Data Index: 6247004 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9914. Min Act: -0.1700
Data Index: 2870606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9601. Min Act: -0.1700
Data Index: 2002431 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9601. Min Act: -0.1700
Data Index: 7512581 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9601. Min Act: -0.1700
Data Index: 5093842 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9601. Min Act: -0.1700
Data Index: 6971425 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9601. Min Act: -0.1700
Data Index: 8729753 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9601. Min Act: -0.1700
Data Index: 8064710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.8976. Min Act: -0.1700
Data Index: 3714631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9289. Min Act: -0.1700
Data Index: 4818504 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9289. Min Act: -0.1700
Data Index: 3480313 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2414. Min Range: -5.2414
Max Act: 4.9289. Min Act: -0.1700
Data Index: 1653993 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19