Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.7446. Min Act: -0.1700
Data Index: 8000878 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.6509. Min Act: -0.1700
Data Index: 7373489 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.4634. Min Act: -0.1700
Data Index: 7131731 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.4321. Min Act: -0.1700
Data Index: 4305179 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.4321. Min Act: -0.1700
Data Index: 4225889 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.4634. Min Act: -0.1700
Data Index: 1530408 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.4009. Min Act: -0.1700
Data Index: 1775454 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.3071. Min Act: -0.1700
Data Index: 83256 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.3071. Min Act: -0.1700
Data Index: 1292134 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.2759. Min Act: -0.1700
Data Index: 1272511 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.2446. Min Act: -0.1700
Data Index: 6564267 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.2446. Min Act: -0.1700
Data Index: 4146244 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.2134. Min Act: -0.1700
Data Index: 4413858 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.1821. Min Act: -0.1700
Data Index: 1708346 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.1821. Min Act: -0.1700
Data Index: 823736 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.1821. Min Act: -0.1700
Data Index: 4687078 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.1509. Min Act: -0.1700
Data Index: 781260 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.1509. Min Act: -0.1700
Data Index: 3480106 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.1509. Min Act: -0.1700
Data Index: 5986359 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7446. Min Range: -5.7446
Max Act: 5.1196. Min Act: -0.1700
Data Index: 4910094 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19