Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1095. Min Range: -5.1095
Max Act: 5.1095. Min Act: -0.1700
Data Index: 1455253 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1095. Min Range: -5.1095
Max Act: 5.0157. Min Act: -0.1700
Data Index: 3160134 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.8907. Min Act: -0.1700
Data Index: 2507889 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.8907. Min Act: -0.1700
Data Index: 8674918 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.8595. Min Act: -0.1700
Data Index: 91452 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.8282. Min Act: -0.1700
Data Index: 206401 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.8282. Min Act: -0.1700
Data Index: 7748037 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.8282. Min Act: -0.1700
Data Index: 5018607 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7970. Min Act: -0.1700
Data Index: 7485291 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7970. Min Act: -0.1700
Data Index: 98257 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7970. Min Act: -0.1700
Data Index: 3934840 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7657. Min Act: -0.1700
Data Index: 8459090 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7970. Min Act: -0.1700
Data Index: 4290706 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7657. Min Act: -0.1700
Data Index: 6563654 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7345. Min Act: -0.1700
Data Index: 966884 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7032. Min Act: -0.1700
Data Index: 7128799 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.6720. Min Act: -0.1700
Data Index: 4307948 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7032. Min Act: -0.1700
Data Index: 6532240 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7032. Min Act: -0.1700
Data Index: 4920937 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1095. Min Range: -5.1095
Max Act: 4.7032. Min Act: -0.1700
Data Index: 436581 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19