Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 498 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3008. Min Range: -5.3008
Max Act: 5.3008. Min Act: -0.1700
Data Index: 1432916 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3008. Min Range: -5.3008
Max Act: 5.0820. Min Act: -0.1700
Data Index: 6842889 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3008. Min Range: -5.3008
Max Act: 5.1133. Min Act: -0.1700
Data Index: 7316741 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.9570. Min Act: -0.1700
Data Index: 7729878 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.9570. Min Act: -0.1700
Data Index: 7170656 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.9258. Min Act: -0.1700
Data Index: 6884537 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.9258. Min Act: -0.1700
Data Index: 1816474 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8633. Min Act: -0.1700
Data Index: 395886 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8633. Min Act: -0.1700
Data Index: 3860539 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8008. Min Act: -0.1700
Data Index: 5650618 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8320. Min Act: -0.1700
Data Index: 5207435 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8008. Min Act: -0.1700
Data Index: 1525720 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8008. Min Act: -0.1700
Data Index: 7547233 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8008. Min Act: -0.1700
Data Index: 5163337 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.8008. Min Act: -0.1700
Data Index: 7121563 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.7695. Min Act: -0.1700
Data Index: 1733795 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.7695. Min Act: -0.1700
Data Index: 4559077 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.7695. Min Act: -0.1700
Data Index: 5906147 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.7383. Min Act: -0.1700
Data Index: 3029730 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3008. Min Range: -5.3008
Max Act: 4.7070. Min Act: -0.1700
Data Index: 766884 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19