Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2322. Min Range: -6.2322
Max Act: 6.2322. Min Act: -0.1700
Data Index: 6800072 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2322. Min Range: -6.2322
Max Act: 6.0759. Min Act: -0.1700
Data Index: 6491342 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.9509. Min Act: -0.1700
Data Index: 7554989 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.9197. Min Act: -0.1700
Data Index: 6053625 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7947. Min Act: -0.1700
Data Index: 7948975 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7322. Min Act: -0.1700
Data Index: 3089384 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7634. Min Act: -0.1700
Data Index: 5751160 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.7009. Min Act: -0.1700
Data Index: 6150061 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.6384. Min Act: -0.1700
Data Index: 4462592 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.6697. Min Act: -0.1700
Data Index: 3089375 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.6697. Min Act: -0.1700
Data Index: 5047825 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.5759. Min Act: -0.1700
Data Index: 6370568 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.5759. Min Act: -0.1700
Data Index: 4462590 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.5447. Min Act: -0.1700
Data Index: 242422 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.5447. Min Act: -0.1700
Data Index: 5439967 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.5134. Min Act: -0.1700
Data Index: 1421083 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.4509. Min Act: -0.1700
Data Index: 3284339 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.4822. Min Act: -0.1700
Data Index: 7148281 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.4197. Min Act: -0.1700
Data Index: 940925 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2322. Min Range: -6.2322
Max Act: 5.4197. Min Act: -0.1700
Data Index: 1503523 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19