Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1020 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4251. Min Range: -6.4251
Max Act: 6.4251. Min Act: -0.1700
Data Index: 4400841 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4251. Min Range: -6.4251
Max Act: 6.3001. Min Act: -0.1700
Data Index: 6431094 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4251. Min Range: -6.4251
Max Act: 6.0813. Min Act: -0.1700
Data Index: 8814101 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4251. Min Range: -6.4251
Max Act: 6.1126. Min Act: -0.1700
Data Index: 3003985 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4251. Min Range: -6.4251
Max Act: 6.0188. Min Act: -0.1700
Data Index: 2285933 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4251. Min Range: -6.4251
Max Act: 6.0188. Min Act: -0.1700
Data Index: 7122793 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.9563. Min Act: -0.1700
Data Index: 6425073 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.9563. Min Act: -0.1700
Data Index: 8025021 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.8938. Min Act: -0.1700
Data Index: 1921776 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.8938. Min Act: -0.1700
Data Index: 1626137 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7348567 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.8001. Min Act: -0.1700
Data Index: 3849074 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.8001. Min Act: -0.1700
Data Index: 5459180 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.7688. Min Act: -0.1700
Data Index: 3785361 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.7376. Min Act: -0.1700
Data Index: 1874635 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.7063. Min Act: -0.1700
Data Index: 7652503 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.6751. Min Act: -0.1700
Data Index: 7036951 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.7063. Min Act: -0.1700
Data Index: 3130424 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.7063. Min Act: -0.1700
Data Index: 6644373 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4251. Min Range: -6.4251
Max Act: 5.7376. Min Act: -0.1700
Data Index: 7002105 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19