Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3944 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.2592. Min Act: -0.1700
Data Index: 1892927 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 4372925 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 8452442 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 7431417 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 7037044 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 6759785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 4433730 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 6070590 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 8663131 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 723559 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 6655168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 1302530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1967. Min Act: -0.1700
Data Index: 2457178 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1342. Min Act: -0.1700
Data Index: 84072 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.1029. Min Act: -0.1700
Data Index: 3755757 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.0717. Min Act: -0.1700
Data Index: 796677 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.0717. Min Act: -0.1700
Data Index: 1261639 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.0717. Min Act: -0.1700
Data Index: 3674484 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.0717. Min Act: -0.1700
Data Index: 3630076 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2592. Min Range: -4.2592
Max Act: 4.0404. Min Act: -0.1700
Data Index: 548059 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19