Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.9058. Min Act: -0.1700
Data Index: 2521295 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.7494. Min Act: -0.1700
Data Index: 1226520 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.7494. Min Act: -0.1700
Data Index: 2740039 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.6868. Min Act: -0.1700
Data Index: 5193245 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.6868. Min Act: -0.1700
Data Index: 3877332 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.6556. Min Act: -0.1700
Data Index: 4828197 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.6086. Min Act: -0.1700
Data Index: 3132319 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.6243. Min Act: -0.1700
Data Index: 105725 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.5930. Min Act: -0.1700
Data Index: 5191730 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.5616. Min Act: -0.1700
Data Index: 1060371 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.5616. Min Act: -0.1700
Data Index: 7806593 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.5460. Min Act: -0.1700
Data Index: 8358476 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.5460. Min Act: -0.1700
Data Index: 746083 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.5460. Min Act: -0.1700
Data Index: 1758931 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.5147. Min Act: -0.1700
Data Index: 2081589 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.4990. Min Act: -0.1700
Data Index: 1028430 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.4833. Min Act: -0.1700
Data Index: 1654523 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.4990. Min Act: -0.1700
Data Index: 5900155 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.4833. Min Act: -0.1700
Data Index: 5184695 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9058. Min Range: -3.9058
Max Act: 3.4833. Min Act: -0.1700
Data Index: 6704642 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19