Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1681. Min Range: -7.1681
Max Act: 7.1681. Min Act: -0.1700
Data Index: 4302589 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1681. Min Range: -7.1681
Max Act: 7.1369. Min Act: -0.1699
Data Index: 6951268 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1681. Min Range: -7.1681
Max Act: 7.0431. Min Act: -0.1700
Data Index: 7632128 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.8869. Min Act: -0.1700
Data Index: 4293455 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.8869. Min Act: -0.1700
Data Index: 4014989 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.8556. Min Act: -0.1700
Data Index: 1333531 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.8244. Min Act: -0.1700
Data Index: 5969148 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.8244. Min Act: -0.1700
Data Index: 6209204 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7619. Min Act: -0.1700
Data Index: 7928128 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7619. Min Act: -0.1700
Data Index: 6171805 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7306. Min Act: -0.1700
Data Index: 2617562 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7306. Min Act: -0.1700
Data Index: 4454632 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7306. Min Act: -0.1700
Data Index: 7390891 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7306. Min Act: -0.1700
Data Index: 331851 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6994. Min Act: -0.1700
Data Index: 1049508 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6994. Min Act: -0.1700
Data Index: 3991838 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.7306. Min Act: -0.1700
Data Index: 4480120 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6994. Min Act: -0.1700
Data Index: 463192 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6994. Min Act: -0.1700
Data Index: 5971703 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1681. Min Range: -7.1681
Max Act: 6.6994. Min Act: -0.1700
Data Index: 5042832 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19