Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.8667. Min Act: -0.1700
Data Index: 6809216 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.7729. Min Act: -0.1700
Data Index: 373756 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.4604. Min Act: -0.1700
Data Index: 1165040 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.4604. Min Act: -0.1700
Data Index: 7915290 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.4292. Min Act: -0.1700
Data Index: 7991429 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.4292. Min Act: -0.1700
Data Index: 3360954 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.4292. Min Act: -0.1700
Data Index: 8411577 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.3979. Min Act: -0.1700
Data Index: 2407104 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.3667. Min Act: -0.1700
Data Index: 3487349 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.3042. Min Act: -0.1700
Data Index: 2472174 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.3042. Min Act: -0.1700
Data Index: 5288818 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.2417. Min Act: -0.1700
Data Index: 4046834 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.2417. Min Act: -0.1700
Data Index: 6180615 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.2104. Min Act: -0.1700
Data Index: 7835955 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.2104. Min Act: -0.1700
Data Index: 1083037 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.2104. Min Act: -0.1700
Data Index: 1448913 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.1792. Min Act: -0.1700
Data Index: 7548721 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1235091 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1896010 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8667. Min Range: -6.8667
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1214805 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19