Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 984 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5638. Min Act: -0.1700
Data Index: 5104366 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5481. Min Act: -0.1700
Data Index: 3653761 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5638. Min Act: -0.1700
Data Index: 423451 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5011. Min Act: -0.1700
Data Index: 4978756 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.5011. Min Act: -0.1700
Data Index: 6977579 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4855. Min Act: -0.1700
Data Index: 3075234 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4698. Min Act: -0.1700
Data Index: 2663493 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4541. Min Act: -0.1700
Data Index: 7672126 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3914. Min Act: -0.1700
Data Index: 4501752 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4541. Min Act: -0.1700
Data Index: 1028047 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4228. Min Act: -0.1700
Data Index: 5030676 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.4385. Min Act: -0.1700
Data Index: 1020073 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3758. Min Act: -0.1700
Data Index: 4585336 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3601. Min Act: -0.1700
Data Index: 1296690 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3914. Min Act: -0.1700
Data Index: 5217653 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3444. Min Act: -0.1700
Data Index: 6794137 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3758. Min Act: -0.1700
Data Index: 1661926 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3601. Min Act: -0.1700
Data Index: 4009728 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3444. Min Act: -0.1700
Data Index: 2323168 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5638. Min Range: -3.5638
Max Act: 3.3601. Min Act: -0.1700
Data Index: 6964076 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19