Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.2262. Min Act: -0.1700
Data Index: 6803018 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1637. Min Act: -0.1700
Data Index: 1229917 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1324. Min Act: -0.1700
Data Index: 5732732 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1012. Min Act: -0.1700
Data Index: 8603199 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6688607 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1012. Min Act: -0.1700
Data Index: 2247973 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1012. Min Act: -0.1700
Data Index: 857202 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.0699. Min Act: -0.1700
Data Index: 8232584 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.0699. Min Act: -0.1700
Data Index: 6770483 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1012. Min Act: -0.1700
Data Index: 3032762 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.1012. Min Act: -0.1700
Data Index: 2173820 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.0387. Min Act: -0.1700
Data Index: 2807916 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2262. Min Range: -4.2262
Max Act: 4.0074. Min Act: -0.1700
Data Index: 7615413 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2262. Min Range: -4.2262
Max Act: 3.9762. Min Act: -0.1700
Data Index: 3354855 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2262. Min Range: -4.2262
Max Act: 3.9762. Min Act: -0.1700
Data Index: 4385078 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2262. Min Range: -4.2262
Max Act: 3.9762. Min Act: -0.1700
Data Index: 5370149 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2262. Min Range: -4.2262
Max Act: 3.9762. Min Act: -0.1700
Data Index: 7484192 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2262. Min Range: -4.2262
Max Act: 3.9449. Min Act: -0.1700
Data Index: 2100870 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2262. Min Range: -4.2262
Max Act: 3.9762. Min Act: -0.1700
Data Index: 4293418 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2262. Min Range: -4.2262
Max Act: 3.9762. Min Act: -0.1700
Data Index: 288424 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19