Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.6389. Min Act: -0.1700
Data Index: 3256536 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.6077. Min Act: -0.1700
Data Index: 4466245 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.5139. Min Act: -0.1700
Data Index: 5001232 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4827. Min Act: -0.1700
Data Index: 2939059 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4827. Min Act: -0.1700
Data Index: 5506123 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4827. Min Act: -0.1700
Data Index: 3317764 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4827. Min Act: -0.1700
Data Index: 7578748 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4827. Min Act: -0.1700
Data Index: 6930162 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4827. Min Act: -0.1700
Data Index: 7614232 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4202. Min Act: -0.1700
Data Index: 8689854 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4202. Min Act: -0.1700
Data Index: 3531185 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4202. Min Act: -0.1700
Data Index: 1570552 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4514. Min Act: -0.1700
Data Index: 3680771 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4202. Min Act: -0.1700
Data Index: 3208909 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4202. Min Act: -0.1700
Data Index: 6778187 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4514. Min Act: -0.1700
Data Index: 3942912 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.3889. Min Act: -0.1700
Data Index: 6185226 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4514. Min Act: -0.1700
Data Index: 924332 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.4202. Min Act: -0.1700
Data Index: 7224983 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6389. Min Range: -4.6389
Max Act: 4.3889. Min Act: -0.1700
Data Index: 67811 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19