Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.6762. Min Act: -0.1700
Data Index: 371393 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.6450. Min Act: -0.1700
Data Index: 2353312 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5825. Min Act: -0.1700
Data Index: 8794637 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5825. Min Act: -0.1700
Data Index: 1670868 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5512. Min Act: -0.1699
Data Index: 3392047 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5512. Min Act: -0.1700
Data Index: 474671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5200. Min Act: -0.1700
Data Index: 7083248 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5512. Min Act: -0.1700
Data Index: 222761 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5512. Min Act: -0.1700
Data Index: 164006 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5200. Min Act: -0.1700
Data Index: 3565975 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5200. Min Act: -0.1700
Data Index: 2246154 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5512. Min Act: -0.1698
Data Index: 3618960 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5200. Min Act: -0.1700
Data Index: 3549809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5512. Min Act: -0.1700
Data Index: 7509303 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5512. Min Act: -0.1700
Data Index: 1050504 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5200. Min Act: -0.1700
Data Index: 1050506 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.5200. Min Act: -0.1700
Data Index: 1672374 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.4887. Min Act: -0.1700
Data Index: 7018261 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.4887. Min Act: -0.1700
Data Index: 4610342 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6762. Min Range: -5.6762
Max Act: 5.4887. Min Act: -0.1700
Data Index: 5521663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19