Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4986 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4712. Min Act: -0.1700
Data Index: 93676 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4399. Min Act: -0.1700
Data Index: 5733513 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4087. Min Act: -0.1700
Data Index: 3978195 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2837. Min Act: -0.1700
Data Index: 3550530 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2524. Min Act: -0.1700
Data Index: 8061686 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 8729175 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 1002183 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 3243224 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 8729177 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 3449138 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.1899. Min Act: -0.1700
Data Index: 2461809 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.1274. Min Act: -0.1700
Data Index: 6227412 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.1274. Min Act: -0.1700
Data Index: 1708767 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.1274. Min Act: -0.1700
Data Index: 7159047 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.1274. Min Act: -0.1700
Data Index: 6922135 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0962. Min Act: -0.1700
Data Index: 2985694 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0962. Min Act: -0.1700
Data Index: 924829 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0962. Min Act: -0.1700
Data Index: 6255778 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0649. Min Act: -0.1700
Data Index: 5207298 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0649. Min Act: -0.1700
Data Index: 155672 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19