Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6323 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.6887. Min Act: -0.1700
Data Index: 2139962 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.5950. Min Act: -0.1700
Data Index: 4889880 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.5325. Min Act: -0.1700
Data Index: 5930581 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.4075. Min Act: -0.1700
Data Index: 3788330 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.3762. Min Act: -0.1700
Data Index: 4707298 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.3450. Min Act: -0.1700
Data Index: 620232 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.2825. Min Act: -0.1700
Data Index: 7239219 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.2512. Min Act: -0.1700
Data Index: 2183910 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.2512. Min Act: -0.1700
Data Index: 1226592 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.2200. Min Act: -0.1700
Data Index: 8799530 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.2200. Min Act: -0.1700
Data Index: 5930580 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1887. Min Act: -0.1700
Data Index: 5930584 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1575. Min Act: -0.1700
Data Index: 6541081 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1887. Min Act: -0.1700
Data Index: 2013487 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1575. Min Act: -0.1700
Data Index: 1049588 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1575. Min Act: -0.1700
Data Index: 7573671 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1262. Min Act: -0.1700
Data Index: 5930583 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1262. Min Act: -0.1700
Data Index: 2320201 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1262. Min Act: -0.1700
Data Index: 3170410 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6887. Min Range: -6.6887
Max Act: 6.1262. Min Act: -0.1700
Data Index: 1445510 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19