Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.9755. Min Act: -0.1700
Data Index: 6083766 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.8487. Min Act: -0.1700
Data Index: 3810561 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.8010. Min Act: -0.1700
Data Index: 6111422 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.7372. Min Act: -0.1700
Data Index: 1366037 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.7372. Min Act: -0.1700
Data Index: 4604177 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6892. Min Act: -0.1700
Data Index: 1632960 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6732. Min Act: -0.1700
Data Index: 1811723 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6892. Min Act: -0.1700
Data Index: 6037815 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6732. Min Act: -0.1700
Data Index: 6541169 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6732. Min Act: -0.1700
Data Index: 4001719 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6572. Min Act: -0.1700
Data Index: 6967893 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6411. Min Act: -0.1700
Data Index: 100521 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6411. Min Act: -0.1700
Data Index: 3516198 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6411. Min Act: -0.1700
Data Index: 1075156 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6572. Min Act: -0.1700
Data Index: 7700096 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6411. Min Act: -0.1700
Data Index: 7076980 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6250. Min Act: -0.1700
Data Index: 1902129 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6250. Min Act: -0.1700
Data Index: 6914189 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6090. Min Act: -0.1700
Data Index: 1437255 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9755. Min Range: -2.9755
Max Act: 2.6250. Min Act: -0.1700
Data Index: 322109 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19