Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1867 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.7158. Min Act: -0.1700
Data Index: 8536210 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.5908. Min Act: -0.1700
Data Index: 5581755 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.5283. Min Act: -0.1700
Data Index: 772272 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.4970. Min Act: -0.1700
Data Index: 7428250 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.4658. Min Act: -0.1700
Data Index: 6501688 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.4658. Min Act: -0.1700
Data Index: 3713905 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.4658. Min Act: -0.1700
Data Index: 4755401 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3720. Min Act: -0.1700
Data Index: 3816874 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3720. Min Act: -0.1700
Data Index: 3379742 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3720. Min Act: -0.1700
Data Index: 4368901 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3720. Min Act: -0.1700
Data Index: 6795827 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3095. Min Act: -0.1700
Data Index: 5243776 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.2783. Min Act: -0.1700
Data Index: 1893743 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3095. Min Act: -0.1700
Data Index: 8359580 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3408. Min Act: -0.1700
Data Index: 3806097 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3095. Min Act: -0.1700
Data Index: 5373617 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3095. Min Act: -0.1700
Data Index: 5128462 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3095. Min Act: -0.1700
Data Index: 4469946 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.3095. Min Act: -0.1700
Data Index: 6184821 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7158. Min Range: -5.7158
Max Act: 5.2470. Min Act: -0.1700
Data Index: 5848858 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19