Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0902. Min Range: -12.0902
Max Act: 12.0902. Min Act: -0.1700
Data Index: 547159 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.7152. Min Act: -0.1700
Data Index: 6532219 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.6527. Min Act: -0.1700
Data Index: 6250586 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.6527. Min Act: -0.1700
Data Index: 6820601 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.5902. Min Act: -0.1700
Data Index: 6960695 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.5902. Min Act: -0.1700
Data Index: 5930994 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.5277. Min Act: -0.1700
Data Index: 3866885 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.5277. Min Act: -0.1700
Data Index: 734758 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.5277. Min Act: -0.1700
Data Index: 4734925 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.5277. Min Act: -0.1700
Data Index: 2864830 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.5277. Min Act: -0.1700
Data Index: 6849829 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4652. Min Act: -0.1700
Data Index: 858187 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4652. Min Act: -0.1700
Data Index: 2648708 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4027. Min Act: -0.1700
Data Index: 85104 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4027. Min Act: -0.1700
Data Index: 3658873 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4652. Min Act: -0.1700
Data Index: 4183116 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4027. Min Act: -0.1700
Data Index: 1599369 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4027. Min Act: -0.1700
Data Index: 3342556 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4027. Min Act: -0.1700
Data Index: 6861759 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0902. Min Range: -12.0902
Max Act: 11.4652. Min Act: -0.1700
Data Index: 3154766 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19