Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.1877. Min Act: -0.1700
Data Index: 2653639 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.1565. Min Act: -0.1700
Data Index: 5330629 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.0627. Min Act: -0.1700
Data Index: 3130007 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.0627. Min Act: -0.1700
Data Index: 1343063 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.0627. Min Act: -0.1700
Data Index: 6556826 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.0314. Min Act: -0.1700
Data Index: 5316590 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.0002. Min Act: -0.1700
Data Index: 5919889 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.0002. Min Act: -0.1700
Data Index: 4156548 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1877. Min Range: -4.1877
Max Act: 4.0002. Min Act: -0.1700
Data Index: 8777211 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9377. Min Act: -0.1700
Data Index: 2085599 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9689. Min Act: -0.1700
Data Index: 622193 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9689. Min Act: -0.1700
Data Index: 8364194 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9689. Min Act: -0.1700
Data Index: 5514129 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9689. Min Act: -0.1700
Data Index: 4578322 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9377. Min Act: -0.1700
Data Index: 2062458 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9377. Min Act: -0.1700
Data Index: 558860 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9064. Min Act: -0.1700
Data Index: 6624525 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9064. Min Act: -0.1700
Data Index: 5472633 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9377. Min Act: -0.1700
Data Index: 5028262 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1877. Min Range: -4.1877
Max Act: 3.9064. Min Act: -0.1700
Data Index: 5316591 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19