Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.2999. Min Act: -0.1700
Data Index: 2472949 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.2687. Min Act: -0.1700
Data Index: 5142936 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.2374. Min Act: -0.1700
Data Index: 3148657 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1749. Min Act: -0.1700
Data Index: 5308726 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.2062. Min Act: -0.1700
Data Index: 4788609 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1437. Min Act: -0.1700
Data Index: 847108 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.2062. Min Act: -0.1700
Data Index: 4276965 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1749. Min Act: -0.1700
Data Index: 8307099 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1437. Min Act: -0.1700
Data Index: 8402186 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1437. Min Act: -0.1700
Data Index: 3948499 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1124. Min Act: -0.1700
Data Index: 8429452 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1124. Min Act: -0.1700
Data Index: 5206931 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1437. Min Act: -0.1700
Data Index: 3311604 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1437. Min Act: -0.1700
Data Index: 6223223 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1437. Min Act: -0.1700
Data Index: 1273385 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1124. Min Act: -0.1700
Data Index: 611105 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1437. Min Act: -0.1700
Data Index: 6184427 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1124. Min Act: -0.1700
Data Index: 6248114 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1124. Min Act: -0.1700
Data Index: 6564507 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2999. Min Range: -4.2999
Max Act: 4.1124. Min Act: -0.1700
Data Index: 3295867 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19