Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.5058. Min Act: -0.1700
Data Index: 5410740 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.4744. Min Act: -0.1700
Data Index: 5500334 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.4431. Min Act: -0.1700
Data Index: 5506798 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.4117. Min Act: -0.1700
Data Index: 816979 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.4274. Min Act: -0.1700
Data Index: 7786629 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.4117. Min Act: -0.1700
Data Index: 4534646 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.4274. Min Act: -0.1700
Data Index: 318058 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3804. Min Act: -0.1700
Data Index: 4558415 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3647. Min Act: -0.1700
Data Index: 1348214 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3961. Min Act: -0.1700
Data Index: 4322864 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3804. Min Act: -0.1700
Data Index: 4322863 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3804. Min Act: -0.1700
Data Index: 4120380 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3647. Min Act: -0.1700
Data Index: 6152595 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3647. Min Act: -0.1700
Data Index: 2674031 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3804. Min Act: -0.1700
Data Index: 7491992 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3647. Min Act: -0.1700
Data Index: 3911720 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3490. Min Act: -0.1700
Data Index: 2197957 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3647. Min Act: -0.1700
Data Index: 2175998 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3647. Min Act: -0.1700
Data Index: 4322862 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5058. Min Range: -3.5058
Max Act: 3.3333. Min Act: -0.1700
Data Index: 1732372 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19