Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1764 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.8783. Min Act: -0.1700
Data Index: 6840816 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.9095. Min Act: -0.1700
Data Index: 6882725 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.8783. Min Act: -0.1700
Data Index: 4526710 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.6908. Min Act: -0.1700
Data Index: 2780859 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.6908. Min Act: -0.1700
Data Index: 8589337 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.6908. Min Act: -0.1700
Data Index: 4973531 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.6283. Min Act: -0.1700
Data Index: 1911687 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5970. Min Act: -0.1700
Data Index: 7772414 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.6283. Min Act: -0.1700
Data Index: 7707575 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5345. Min Act: -0.1700
Data Index: 5165719 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5345. Min Act: -0.1700
Data Index: 5070487 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5658. Min Act: -0.1700
Data Index: 1035695 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5345. Min Act: -0.1700
Data Index: 1282788 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5345. Min Act: -0.1700
Data Index: 4895033 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5033. Min Act: -0.1700
Data Index: 3345818 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.5033. Min Act: -0.1700
Data Index: 5596022 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.4720. Min Act: -0.1700
Data Index: 1564824 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.4720. Min Act: -0.1700
Data Index: 1637666 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.4720. Min Act: -0.1700
Data Index: 7683495 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9095. Min Range: -5.9095
Max Act: 5.4720. Min Act: -0.1700
Data Index: 4581394 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19