Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.8909. Min Act: -0.1700
Data Index: 6806756 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.7971. Min Act: -0.1700
Data Index: 8215195 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.7658. Min Act: -0.1700
Data Index: 1985437 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.7345. Min Act: -0.1700
Data Index: 6766384 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.7501. Min Act: -0.1700
Data Index: 5448340 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.6876. Min Act: -0.1700
Data Index: 7977753 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.6563. Min Act: -0.1700
Data Index: 5232053 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.6406. Min Act: -0.1700
Data Index: 4566896 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.6093. Min Act: -0.1700
Data Index: 4255996 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.6250. Min Act: -0.1700
Data Index: 2870104 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.6093. Min Act: -0.1700
Data Index: 7518054 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.6250. Min Act: -0.1700
Data Index: 1819125 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5780. Min Act: -0.1700
Data Index: 1761779 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5937. Min Act: -0.1700
Data Index: 3241148 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5937. Min Act: -0.1700
Data Index: 6300989 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5937. Min Act: -0.1700
Data Index: 7940329 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5780. Min Act: -0.1700
Data Index: 7402345 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5624. Min Act: -0.1700
Data Index: 7471573 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5624. Min Act: -0.1700
Data Index: 7392382 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8909. Min Range: -3.8909
Max Act: 3.5624. Min Act: -0.1700
Data Index: 7280883 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19