Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.9430. Min Act: -0.1700
Data Index: 1702954 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.7555. Min Act: -0.1700
Data Index: 3195933 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.6305. Min Act: -0.1700
Data Index: 5524818 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.5367. Min Act: -0.1700
Data Index: 7370322 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.5367. Min Act: -0.1700
Data Index: 4382627 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.5055. Min Act: -0.1700
Data Index: 8144035 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4742. Min Act: -0.1700
Data Index: 3610645 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.5055. Min Act: -0.1700
Data Index: 8097553 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4430. Min Act: -0.1700
Data Index: 1766244 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4742. Min Act: -0.1700
Data Index: 398514 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4742. Min Act: -0.1700
Data Index: 5394998 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4742. Min Act: -0.1700
Data Index: 2673576 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4117. Min Act: -0.1700
Data Index: 400687 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4430. Min Act: -0.1700
Data Index: 7370323 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4430. Min Act: -0.1700
Data Index: 4742592 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.5680. Min Act: -0.1700
Data Index: 1541367 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.3805. Min Act: -0.1700
Data Index: 6336186 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.3805. Min Act: -0.1700
Data Index: 2723707 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.4117. Min Act: -0.1700
Data Index: 3403006 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9430. Min Range: -5.9430
Max Act: 5.3805. Min Act: -0.1700
Data Index: 2669867 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19