Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3780 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.2142. Min Act: -0.1700
Data Index: 8519708 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0892. Min Act: -0.1700
Data Index: 1309665 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0892. Min Act: -0.1700
Data Index: 4916876 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0580. Min Act: -0.1700
Data Index: 3218050 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0267. Min Act: -0.1700
Data Index: 4383509 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2142. Min Range: -5.2142
Max Act: 5.0267. Min Act: -0.1700
Data Index: 2543837 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 814375 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 1309664 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 854351 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 1149441 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 6025110 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 3500414 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9330. Min Act: -0.1700
Data Index: 4423908 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9330. Min Act: -0.1700
Data Index: 7061563 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9330. Min Act: -0.1700
Data Index: 662533 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9642. Min Act: -0.1700
Data Index: 3867421 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9017. Min Act: -0.1700
Data Index: 7665612 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9017. Min Act: -0.1700
Data Index: 8169998 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.9017. Min Act: -0.1700
Data Index: 7617083 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2142. Min Range: -5.2142
Max Act: 4.8705. Min Act: -0.1700
Data Index: 7142556 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19