Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0951. Min Act: -0.1700
Data Index: 933181 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0793. Min Act: -0.1700
Data Index: 8269295 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0636. Min Act: -0.1700
Data Index: 4180741 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0320. Min Act: -0.1700
Data Index: 3475072 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0162. Min Act: -0.1700
Data Index: 5015244 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0162. Min Act: -0.1700
Data Index: 2288969 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0162. Min Act: -0.1700
Data Index: 3328362 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0004. Min Act: -0.1700
Data Index: 4305944 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0004. Min Act: -0.1700
Data Index: 6837642 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0951. Min Range: -3.0951
Max Act: 3.0004. Min Act: -0.1700
Data Index: 1666593 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9846. Min Act: -0.1700
Data Index: 8205904 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9688. Min Act: -0.1700
Data Index: 6720933 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9688. Min Act: -0.1700
Data Index: 7357690 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9530. Min Act: -0.1700
Data Index: 3141870 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9530. Min Act: -0.1700
Data Index: 8249899 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9530. Min Act: -0.1700
Data Index: 5547154 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9530. Min Act: -0.1700
Data Index: 7381046 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9371. Min Act: -0.1700
Data Index: 8172675 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9530. Min Act: -0.1700
Data Index: 7377549 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0951. Min Range: -3.0951
Max Act: 2.9371. Min Act: -0.1700
Data Index: 668657 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19