Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2569 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8392. Min Act: -0.1700
Data Index: 518009 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8392. Min Act: -0.1645
Data Index: 4607525 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8306. Min Act: -0.1700
Data Index: 6778584 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8306. Min Act: -0.1700
Data Index: 6741300 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8306. Min Act: -0.1689
Data Index: 3260137 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8220. Min Act: -0.1700
Data Index: 1946826 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8306. Min Act: -0.1700
Data Index: 4554995 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8134. Min Act: -0.1700
Data Index: 1707380 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7962. Min Act: -0.1700
Data Index: 7075868 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8134. Min Act: -0.1700
Data Index: 5768585 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.8048. Min Act: -0.1700
Data Index: 298439 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7790. Min Act: -0.1700
Data Index: 8421873 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7790. Min Act: -0.1700
Data Index: 4696969 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7790. Min Act: -0.1700
Data Index: 6063469 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7790. Min Act: -0.1700
Data Index: 7076671 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7876. Min Act: -0.1700
Data Index: 4710930 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7704. Min Act: -0.1700
Data Index: 5646869 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7704. Min Act: -0.1700
Data Index: 1646766 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7617. Min Act: -0.1700
Data Index: 5903188 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8392. Min Range: -1.8392
Max Act: 1.7704. Min Act: -0.1700
Data Index: 2912612 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19