Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 39 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.2604. Min Act: -0.1700
Data Index: 5984508 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.1979. Min Act: -0.1700
Data Index: 2994677 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.0416. Min Act: -0.1700
Data Index: 3506034 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2604. Min Range: -6.2604
Max Act: 6.0104. Min Act: -0.1700
Data Index: 6650710 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.9791. Min Act: -0.1700
Data Index: 6133341 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.8541. Min Act: -0.1700
Data Index: 8635499 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7604. Min Act: -0.1700
Data Index: 7675800 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7604. Min Act: -0.1700
Data Index: 5393226 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6979. Min Act: -0.1700
Data Index: 5920932 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7291. Min Act: -0.1700
Data Index: 829215 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7291. Min Act: -0.1700
Data Index: 3847072 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7291. Min Act: -0.1700
Data Index: 8507482 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.7291. Min Act: -0.1700
Data Index: 1565376 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6979. Min Act: -0.1700
Data Index: 6571323 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6979. Min Act: -0.1700
Data Index: 3198382 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6666. Min Act: -0.1700
Data Index: 270869 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6666. Min Act: -0.1700
Data Index: 2540540 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6354. Min Act: -0.1700
Data Index: 1526219 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6354. Min Act: -0.1700
Data Index: 8325775 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2604. Min Range: -6.2604
Max Act: 5.6979. Min Act: -0.1700
Data Index: 5588605 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19