Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.8057. Min Act: -0.1700
Data Index: 6685290 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3836795 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.7745. Min Act: -0.1700
Data Index: 2831232 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.6807. Min Act: -0.1700
Data Index: 8506849 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.6182. Min Act: -0.1700
Data Index: 6249699 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.5557. Min Act: -0.1700
Data Index: 1884288 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.4620. Min Act: -0.1700
Data Index: 4361962 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3995. Min Act: -0.1700
Data Index: 670111 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3995. Min Act: -0.1700
Data Index: 278175 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.4307. Min Act: -0.1700
Data Index: 4950651 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3370. Min Act: -0.1700
Data Index: 2882340 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3057. Min Act: -0.1700
Data Index: 4395264 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3370. Min Act: -0.1700
Data Index: 3916287 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3995. Min Act: -0.1700
Data Index: 4361956 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3057. Min Act: -0.1700
Data Index: 1073312 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.2432. Min Act: -0.1700
Data Index: 7928533 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.2745. Min Act: -0.1700
Data Index: 2135609 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.3057. Min Act: -0.1700
Data Index: 649931 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.2745. Min Act: -0.1700
Data Index: 6520898 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8057. Min Range: -5.8057
Max Act: 5.2432. Min Act: -0.1700
Data Index: 3163880 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19