Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2432 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4821. Min Act: -0.1700
Data Index: 1328838 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4508. Min Act: -0.1700
Data Index: 7011002 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3258. Min Act: -0.1700
Data Index: 4267460 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2633. Min Act: -0.1700
Data Index: 4970992 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2321. Min Act: -0.1700
Data Index: 2564762 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2008. Min Act: -0.1700
Data Index: 833493 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2321. Min Act: -0.1700
Data Index: 6150052 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2321. Min Act: -0.1700
Data Index: 1333931 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2321. Min Act: -0.1700
Data Index: 1073870 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2008. Min Act: -0.1700
Data Index: 7316277 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1696. Min Act: -0.1700
Data Index: 8290492 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1696. Min Act: -0.1700
Data Index: 2039440 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1696. Min Act: -0.1700
Data Index: 5791274 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1383. Min Act: -0.1700
Data Index: 3357830 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1696. Min Act: -0.1700
Data Index: 6586547 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1071. Min Act: -0.1700
Data Index: 7866652 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1696. Min Act: -0.1700
Data Index: 8126065 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1383. Min Act: -0.1700
Data Index: 7518966 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1696. Min Act: -0.1700
Data Index: 201757 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1071. Min Act: -0.1700
Data Index: 5037322 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19