Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4072 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8549. Min Act: -0.1700
Data Index: 1437317 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8708. Min Act: -0.1700
Data Index: 5414301 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8390. Min Act: -0.1700
Data Index: 8109917 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8072. Min Act: -0.1700
Data Index: 6515110 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8072. Min Act: -0.1700
Data Index: 11060 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8072. Min Act: -0.1700
Data Index: 1964046 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8231. Min Act: -0.1700
Data Index: 3683749 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7913. Min Act: -0.1700
Data Index: 6436780 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7913. Min Act: -0.1700
Data Index: 2549742 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7913. Min Act: -0.1700
Data Index: 8534563 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7913. Min Act: -0.1700
Data Index: 4665985 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7913. Min Act: -0.1700
Data Index: 8321924 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7913. Min Act: -0.1700
Data Index: 821717 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.8072. Min Act: -0.1700
Data Index: 8134522 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7753. Min Act: -0.1700
Data Index: 4703059 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7913. Min Act: -0.1700
Data Index: 1384737 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7753. Min Act: -0.1700
Data Index: 5535654 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7753. Min Act: -0.1700
Data Index: 1811576 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7594. Min Act: -0.1700
Data Index: 1198857 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8708. Min Range: -2.8708
Max Act: 2.7753. Min Act: -0.1700
Data Index: 3785704 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19