Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2607 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.4492. Min Act: -0.1700
Data Index: 1231965 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1680. Min Act: -0.1700
Data Index: 4909242 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1680. Min Act: -0.1700
Data Index: 5350729 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1680. Min Act: -0.1700
Data Index: 4259155 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1992. Min Act: -0.1700
Data Index: 4900623 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1367. Min Act: -0.1700
Data Index: 6604052 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1680. Min Act: -0.1700
Data Index: 8257590 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1367. Min Act: -0.1700
Data Index: 975084 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.1055. Min Act: -0.1700
Data Index: 5571824 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0742. Min Act: -0.1700
Data Index: 2618177 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0117. Min Act: -0.1700
Data Index: 2669678 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0430. Min Act: -0.1700
Data Index: 6123973 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0430. Min Act: -0.1700
Data Index: 6302782 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9805. Min Act: -0.1700
Data Index: 1093403 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9805. Min Act: -0.1700
Data Index: 4227219 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9805. Min Act: -0.1700
Data Index: 8073581 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4492. Min Range: -6.4492
Max Act: 6.0117. Min Act: -0.1700
Data Index: 3148420 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9805. Min Act: -0.1700
Data Index: 6796412 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9492. Min Act: -0.1700
Data Index: 8062771 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4492. Min Range: -6.4492
Max Act: 5.9492. Min Act: -0.1700
Data Index: 6539447 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19