Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5561. Min Range: -8.5561
Max Act: 8.5561. Min Act: -0.1700
Data Index: 8813619 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5561. Min Range: -8.5561
Max Act: 8.1498. Min Act: -0.1700
Data Index: 1040986 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5561. Min Range: -8.5561
Max Act: 8.0561. Min Act: -0.1700
Data Index: 3654590 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.9936. Min Act: -0.1700
Data Index: 1310060 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.9623. Min Act: -0.1700
Data Index: 7170579 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.9623. Min Act: -0.1700
Data Index: 2245967 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.8373. Min Act: -0.1700
Data Index: 5864486 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.8373. Min Act: -0.1700
Data Index: 3475131 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.8061. Min Act: -0.1700
Data Index: 226563 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.8686. Min Act: -0.1700
Data Index: 4324681 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.7748. Min Act: -0.1700
Data Index: 7128787 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.7748. Min Act: -0.1700
Data Index: 5099062 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.7436. Min Act: -0.1700
Data Index: 1285187 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.6811. Min Act: -0.1700
Data Index: 2133423 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.6498. Min Act: -0.1700
Data Index: 6671124 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.6498. Min Act: -0.1700
Data Index: 1663970 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.6498. Min Act: -0.1700
Data Index: 4717283 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.5873. Min Act: -0.1700
Data Index: 3471434 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.6186. Min Act: -0.1700
Data Index: 8173191 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5561. Min Range: -8.5561
Max Act: 7.5873. Min Act: -0.1700
Data Index: 4339629 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19