Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.3655. Min Range: -9.3655
Max Act: 9.3655. Min Act: -0.1700
Data Index: 6545975 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3655. Min Range: -9.3655
Max Act: 9.1780. Min Act: -0.1700
Data Index: 8245158 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3655. Min Range: -9.3655
Max Act: 8.1780. Min Act: -0.1700
Data Index: 7982505 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.8030. Min Act: -0.1700
Data Index: 7678616 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3655. Min Range: -9.3655
Max Act: 8.7405. Min Act: -0.1700
Data Index: 5887840 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.3655. Min Act: -0.1700
Data Index: 195303 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.3343. Min Act: -0.1700
Data Index: 3134125 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3655. Min Range: -9.3655
Max Act: 6.9280. Min Act: -0.1700
Data Index: 161319 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.2405. Min Act: -0.1700
Data Index: 8600784 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.4280. Min Act: -0.1700
Data Index: 6750019 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3655. Min Range: -9.3655
Max Act: 6.6780. Min Act: -0.1700
Data Index: 312071 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.1155. Min Act: -0.1700
Data Index: 608251 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3655. Min Range: -9.3655
Max Act: 6.4593. Min Act: -0.1700
Data Index: 6729244 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.0843. Min Act: -0.1700
Data Index: 828863 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.1155. Min Act: -0.1700
Data Index: 2430603 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3655. Min Range: -9.3655
Max Act: 6.7718. Min Act: -0.1700
Data Index: 3189957 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.0218. Min Act: -0.1700
Data Index: 8475916 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.0218. Min Act: -0.1700
Data Index: 4608962 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3655. Min Range: -9.3655
Max Act: 7.0843. Min Act: -0.1700
Data Index: 2670037 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3655. Min Range: -9.3655
Max Act: 6.9905. Min Act: -0.1700
Data Index: 5119370 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19