Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2653 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.1353. Min Act: -0.1700
Data Index: 6776887 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.1195. Min Act: -0.1700
Data Index: 2546588 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.1195. Min Act: -0.1700
Data Index: 7086910 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.1038. Min Act: -0.1700
Data Index: 6147804 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0880. Min Act: -0.1700
Data Index: 589693 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0723. Min Act: -0.1700
Data Index: 7186657 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0565. Min Act: -0.1700
Data Index: 642904 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0723. Min Act: -0.1700
Data Index: 7912947 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0723. Min Act: -0.1700
Data Index: 5220717 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0249. Min Act: -0.1700
Data Index: 7159905 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0091. Min Act: -0.1700
Data Index: 1847234 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9933. Min Act: -0.1700
Data Index: 6446502 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9775. Min Act: -0.1700
Data Index: 3095523 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1353. Min Range: -3.1353
Max Act: 3.0091. Min Act: -0.1700
Data Index: 6295150 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9933. Min Act: -0.1700
Data Index: 6245355 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9933. Min Act: -0.1700
Data Index: 4060513 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9933. Min Act: -0.1700
Data Index: 7491303 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9933. Min Act: -0.1700
Data Index: 5116577 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9458. Min Act: -0.1700
Data Index: 1415413 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1353. Min Range: -3.1353
Max Act: 2.9458. Min Act: -0.1700
Data Index: 3587508 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19