Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.7900. Min Act: -0.1700
Data Index: 4717650 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.6338. Min Act: -0.1700
Data Index: 1136493 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5713. Min Act: -0.1700
Data Index: 8457899 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5400. Min Act: -0.1700
Data Index: 2775946 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5400. Min Act: -0.1700
Data Index: 1161373 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5088. Min Act: -0.1700
Data Index: 6452424 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5088. Min Act: -0.1700
Data Index: 7403536 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5088. Min Act: -0.1700
Data Index: 7402438 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5088. Min Act: -0.1700
Data Index: 1561429 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5088. Min Act: -0.1700
Data Index: 176519 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.5088. Min Act: -0.1700
Data Index: 8118236 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.4463. Min Act: -0.1700
Data Index: 8486146 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.4775. Min Act: -0.1700
Data Index: 6194723 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.4775. Min Act: -0.1700
Data Index: 3594306 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.4463. Min Act: -0.1700
Data Index: 2810612 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.4150. Min Act: -0.1700
Data Index: 2665847 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.4463. Min Act: -0.1700
Data Index: 6109413 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.4463. Min Act: -0.1700
Data Index: 3104846 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.3525. Min Act: -0.1700
Data Index: 860311 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7900. Min Range: -6.7900
Max Act: 6.3838. Min Act: -0.1700
Data Index: 880065 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19