Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.4984. Min Act: -0.1700
Data Index: 8464483 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.4359. Min Act: -0.1700
Data Index: 8464482 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.4359. Min Act: -0.1700
Data Index: 8336472 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.3734. Min Act: -0.1700
Data Index: 8167654 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.3422. Min Act: -0.1700
Data Index: 5555931 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.4047. Min Act: -0.1700
Data Index: 256559 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.3734. Min Act: -0.1700
Data Index: 8336471 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.1234. Min Act: -0.1700
Data Index: 6255775 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.0921. Min Act: -0.1700
Data Index: 3884185 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4984. Min Range: -4.4984
Max Act: 4.0296. Min Act: -0.1700
Data Index: 3916147 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9984. Min Act: -0.1700
Data Index: 3583502 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9984. Min Act: -0.1700
Data Index: 7499031 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9984. Min Act: -0.1700
Data Index: 4508550 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9984. Min Act: -0.1700
Data Index: 834865 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9358. Min Act: -0.1700
Data Index: 909090 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9358. Min Act: -0.1700
Data Index: 356034 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9984. Min Act: -0.1700
Data Index: 7075091 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9671. Min Act: -0.1700
Data Index: 3889427 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9671. Min Act: -0.1700
Data Index: 208336 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4984. Min Range: -4.4984
Max Act: 3.9984. Min Act: -0.1700
Data Index: 7828722 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19