Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.1052. Min Act: -0.1700
Data Index: 567859 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 4575840 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.1052. Min Act: -0.1700
Data Index: 4646186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.1052. Min Act: -0.1700
Data Index: 775807 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.1052. Min Act: -0.1700
Data Index: 5672641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.1052. Min Act: -0.1700
Data Index: 5852469 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 4301499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 1454982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 8700591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 6878083 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 3506113 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 6181941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 4778512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0739. Min Act: -0.1700
Data Index: 1471222 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0427. Min Act: -0.1700
Data Index: 1707923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0114. Min Act: -0.1700
Data Index: 4118660 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0427. Min Act: -0.1700
Data Index: 1817866 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0427. Min Act: -0.1700
Data Index: 2067517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0427. Min Act: -0.1700
Data Index: 2111603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1052. Min Range: -4.1052
Max Act: 4.0427. Min Act: -0.1700
Data Index: 2118473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19