Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1625 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.8353. Min Act: -0.1700
Data Index: 5558671 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.7415. Min Act: -0.1700
Data Index: 5555778 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.7103. Min Act: -0.1700
Data Index: 8291313 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.6790. Min Act: -0.1700
Data Index: 1117034 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.6790. Min Act: -0.1700
Data Index: 5548773 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.6478. Min Act: -0.1700
Data Index: 5548765 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.6478. Min Act: -0.1700
Data Index: 6924719 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.6165. Min Act: -0.1700
Data Index: 4744828 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.6478. Min Act: -0.1700
Data Index: 6924735 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.5540. Min Act: -0.1700
Data Index: 559263 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.4915. Min Act: -0.1700
Data Index: 7358902 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.4915. Min Act: -0.1700
Data Index: 2288991 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.4603. Min Act: -0.1700
Data Index: 5628219 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.3978. Min Act: -0.1700
Data Index: 3175368 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.3978. Min Act: -0.1700
Data Index: 1599101 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.4290. Min Act: -0.1700
Data Index: 4451802 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.3978. Min Act: -0.1700
Data Index: 2566681 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.3665. Min Act: -0.1700
Data Index: 1755005 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.3040. Min Act: -0.1700
Data Index: 784466 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8353. Min Range: -4.8353
Max Act: 4.3353. Min Act: -0.1700
Data Index: 1373446 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19