Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 822 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5462. Min Range: -6.5462
Max Act: 6.5462. Min Act: -0.1700
Data Index: 1973285 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.6712. Min Act: -0.1700
Data Index: 8241535 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.6712. Min Act: -0.1700
Data Index: 1570012 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.6712. Min Act: -0.1700
Data Index: 1624138 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5774. Min Act: -0.1700
Data Index: 4574337 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 4033885 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5774. Min Act: -0.1700
Data Index: 484527 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5149. Min Act: -0.1700
Data Index: 1958606 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 3193657 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 7580745 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5774. Min Act: -0.1700
Data Index: 694410 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.5462. Min Act: -0.1700
Data Index: 5935536 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4837. Min Act: -0.1700
Data Index: 7330873 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4837. Min Act: -0.1700
Data Index: 8719613 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4837. Min Act: -0.1700
Data Index: 7086454 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4524. Min Act: -0.1700
Data Index: 7322442 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4524. Min Act: -0.1700
Data Index: 1331181 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4212. Min Act: -0.1700
Data Index: 4041152 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4212. Min Act: -0.1700
Data Index: 2625334 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5462. Min Range: -6.5462
Max Act: 5.4212. Min Act: -0.1700
Data Index: 5726068 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19