Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5470 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.4937. Min Act: -0.1700
Data Index: 2838082 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.4937. Min Act: -0.1700
Data Index: 5409893 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.4624. Min Act: -0.1700
Data Index: 6121527 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.4467. Min Act: -0.1700
Data Index: 3311461 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.4154. Min Act: -0.1700
Data Index: 8502667 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.3840. Min Act: -0.1700
Data Index: 3957494 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.3526. Min Act: -0.1700
Data Index: 6021946 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.3056. Min Act: -0.1700
Data Index: 4906783 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.3213. Min Act: -0.1700
Data Index: 8671497 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2899. Min Act: -0.1700
Data Index: 4551644 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2899. Min Act: -0.1700
Data Index: 8000800 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2899. Min Act: -0.1700
Data Index: 6409522 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2742. Min Act: -0.1700
Data Index: 7703642 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2742. Min Act: -0.1700
Data Index: 3177068 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2899. Min Act: -0.1700
Data Index: 7006155 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2899. Min Act: -0.1700
Data Index: 1544615 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2585. Min Act: -0.1700
Data Index: 3808879 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2427. Min Act: -0.1700
Data Index: 7354303 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2270. Min Act: -0.1700
Data Index: 1249880 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4937. Min Range: -3.4937
Max Act: 3.2427. Min Act: -0.1700
Data Index: 4615939 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19