Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.3389. Min Act: -0.1700
Data Index: 2312012 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 6866142 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.3075. Min Act: -0.1700
Data Index: 2210946 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.3075. Min Act: -0.1700
Data Index: 3947727 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.3075. Min Act: -0.1700
Data Index: 1060461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.3075. Min Act: -0.1700
Data Index: 79725 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.3075. Min Act: -0.1700
Data Index: 3951630 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.3075. Min Act: -0.1700
Data Index: 4542447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2447. Min Act: -0.1700
Data Index: 3746475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 1738787 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 3722652 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 4935520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 1256299 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 3028623 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 4069352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 1696662 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 2945913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 1067967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 380452 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3389. Min Range: -3.3389
Max Act: 3.2761. Min Act: -0.1700
Data Index: 2628986 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19