Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5644 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.6949. Min Act: -0.1700
Data Index: 5465320 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.6324. Min Act: -0.1700
Data Index: 5504967 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.5699. Min Act: -0.1700
Data Index: 2305773 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.5387. Min Act: -0.1700
Data Index: 4016606 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.5074. Min Act: -0.1700
Data Index: 3651256 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3512. Min Act: -0.1700
Data Index: 1801585 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3512. Min Act: -0.1700
Data Index: 6156561 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3512. Min Act: -0.1700
Data Index: 2380790 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3199. Min Act: -0.1700
Data Index: 5569790 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3199. Min Act: -0.1700
Data Index: 4714403 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2887. Min Act: -0.1700
Data Index: 1792041 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2887. Min Act: -0.1700
Data Index: 4531930 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2574. Min Act: -0.1700
Data Index: 1054155 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2574. Min Act: -0.1700
Data Index: 2947416 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2574. Min Act: -0.1700
Data Index: 6158001 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2262. Min Act: -0.1700
Data Index: 2548608 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2574. Min Act: -0.1700
Data Index: 1196486 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2262. Min Act: -0.1700
Data Index: 1280388 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2262. Min Act: -0.1700
Data Index: 5839646 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.2262. Min Act: -0.1700
Data Index: 5563886 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19