Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8892. Min Range: -8.8892
Max Act: 8.8892. Min Act: -0.1700
Data Index: 6191649 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.8267. Min Act: -0.1700
Data Index: 1201265 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.3579. Min Act: -0.1700
Data Index: 4013876 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.3579. Min Act: -0.1700
Data Index: 2838340 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.3267. Min Act: -0.1700
Data Index: 8412746 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.3267. Min Act: -0.1700
Data Index: 7120293 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.2329. Min Act: -0.1700
Data Index: 951784 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 946873 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.2017. Min Act: -0.1700
Data Index: 4098872 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.0767. Min Act: -0.1700
Data Index: 7342837 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.0767. Min Act: -0.1700
Data Index: 80283 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.0454. Min Act: -0.1700
Data Index: 1583533 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.0454. Min Act: -0.1700
Data Index: 7845097 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.0454. Min Act: -0.1700
Data Index: 8297605 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.0142. Min Act: -0.1700
Data Index: 7891424 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8892. Min Range: -8.8892
Max Act: 7.0142. Min Act: -0.1700
Data Index: 8416679 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8892. Min Range: -8.8892
Max Act: 6.9517. Min Act: -0.1700
Data Index: 293699 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8892. Min Range: -8.8892
Max Act: 6.9517. Min Act: -0.1700
Data Index: 6086342 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8892. Min Range: -8.8892
Max Act: 6.9517. Min Act: -0.1700
Data Index: 8630403 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8892. Min Range: -8.8892
Max Act: 6.9517. Min Act: -0.1700
Data Index: 5672538 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19