Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2543 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.4780. Min Act: -0.1700
Data Index: 5180958 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.4155. Min Act: -0.1700
Data Index: 6047885 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.4155. Min Act: -0.1700
Data Index: 421969 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.4155. Min Act: -0.1700
Data Index: 8348967 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.3217. Min Act: -0.1700
Data Index: 7559823 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.2280. Min Act: -0.1700
Data Index: 4565693 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1967. Min Act: -0.1700
Data Index: 5431693 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1967. Min Act: -0.1700
Data Index: 5537067 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.2280. Min Act: -0.1700
Data Index: 1037741 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.2280. Min Act: -0.1700
Data Index: 4117752 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1342. Min Act: -0.1700
Data Index: 4858795 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1342. Min Act: -0.1700
Data Index: 4780946 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1655. Min Act: -0.1700
Data Index: 8043030 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1342. Min Act: -0.1700
Data Index: 1901853 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1967. Min Act: -0.1700
Data Index: 5481060 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1342. Min Act: -0.1700
Data Index: 7611962 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1342. Min Act: -0.1700
Data Index: 4009979 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1342. Min Act: -0.1700
Data Index: 5128396 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1342. Min Act: -0.1700
Data Index: 4692811 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4780. Min Range: -4.4780
Max Act: 4.1029. Min Act: -0.1700
Data Index: 5929265 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19